Daily Papers

Modern Lean theorem provers achieve strong performance only with substantial training and inference compute, driven in part by scarce verified proof data and the long reasoning traces of formal proof search, making both supervised fine-tuning (SFT) and sampling expensive. We introduce Pythagoras-Prover, a compute-efficient open-source family of Lean theorem provers built for practical compute budgets. The family spans two generation paradigms: autoregressive models at 4B and 32B parameters, and a first proof-of-concept diffusion-based prover (4B) that iteratively refines Lean proofs at inference time. For training efficiency, we build a Lean-verified corpus stratified into easy, medium, and hard problems for curriculum SFT, so models acquire proof skills progressively from shorter, simpler proofs to longer, harder ones. During SFT, a dynamic proof-reasoning filtering scheme preserves informative proof traces while keeping each instance within an 8k-token context budget. We also introduce Augmented Lean Formalisation (ALF), which expands scarce verified corpora into variants of formal statements, populated via self-distillation for extra training signal without formally verifying every mutated instance. By perturbing known problems while preserving their formal character, ALF reduces reliance on any statement's surface form. Empirically, Pythagoras-Prover-4B surpasses DeepSeek-Prover-V2-671B at pass@32 on MiniF2F-Test (86.1% vs 82.4%) with ~167x fewer parameters, while Pythagoras-Prover-32B sets the open-source state of the art at 93.0% on MiniF2F-Test and solves 93 of 672 PutnamBench problems. We release MiniF2F-ALF, an ALF-mutated contamination-sensitive benchmark on which every evaluated model loses accuracy; here our 32B remains strongest and our 4B matches the prior state of the art, Goedel-Prover-V2-32B.

Building machine translation (MT) systems for low-resource languages is notably difficult due to the scarcity of high-quality data. Although Large Language Models (LLMs) have improved MT system performance, adapting them to lesser-represented languages remains challenging. In-context learning (ICL) may offer novel ways to adapt LLMs for low-resource MT by conditioning models on demonstration at inference time. In this study, we explore scaling low-resource machine translation ICL beyond the few-shot setting to thousands of examples with long-context models. We scale in-context token budget to 1M tokens and compare three types of training corpora used as in-context supervision: monolingual unsupervised data, instruction-style data, and parallel data (English--target and Indonesian--target). Our experiments on Javanese and Sundanese show that gains from additional context saturate quickly and can degrade near the maximum context window, with scaling behavior strongly dependent on corpus type. Notably, some forms of monolingual supervision can be competitive with parallel data, despite the latter offering additional supervision. Overall, our results characterize the effective limits and corpus-type sensitivity of long-context ICL for low-resource MT, highlighting that larger context windows do not necessarily yield proportional quality gains.

Command line interface (CLI) agents are emerging as a practical paradigm for agent-computer interaction over evolving filesystems, executable command line programs, and online execution feedback. Recent work has used reinforcement learning (RL) to learn these interaction abilities from verifiable task feedback, yet few methods exploit the native structured attributes of CLI actions as learning signals. Beyond this underused action structure, CLI learning also couples two bottlenecks for coding agents. First, the agent must identify task-relevant evidence in a large codebase from partial observations. Second, sparse terminal rewards must be assigned to the actions that shape a long multi-turn trajectory. We study these bottlenecks through shell-driven information extraction and file editing tasks. For selective observation, we introduce σ-Reveal, an inference-time mechanism that selects token-budgeted context for the same CLI. For credit assignment, we propose Action Advantage Assignment (A^3), a native agentic RL method that preserves the algorithmic complexity of standard agentic RL. A^3 constructs turn-level advantages from episode-level relative feedback, abstract syntax tree (AST) based action sub-chain residuals, and tree-level trajectory margins. To further evaluate this problem setting, we construct ShellOps, a verifiable dataset suite covering CLI tasks in repository environments.

Ultra-high-resolution (UHR) remote sensing imagery couples kilometer-scale context with query-critical evidence that may occupy only a few pixels. Such vast spatial scale leads to a quadratic explosion of visual tokens and hinders the extraction of information from small objects. Previous works utilize direct downsampling, dense tiling, or global top-k pruning, which either compromise query-critical image details or incur unpredictable compute. In this paper, we propose UHR-BAT, a query-guided and region-faithful token compression framework to efficiently select visual tokens under a strict context budget. Specifically, we leverage text-guided, multi-scale importance estimation for visual tokens, effectively tackling the challenge of achieving precise yet low-cost feature extraction. Furthermore, by introducing region-wise preserve and merge strategies, we mitigate visual token redundancy, further driving down the computational budget. Experimental results show that UHR-BAT achieves state-of-the-art performance across various benchmarks. Code will be available at https://github.com/Yunkaidang/UHR.

LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermediate records and mediating their retrieval adds recurring token and time costs, while omitted or merged details can obscure the original evidence. We ask whether structured memory access requires generation at all. Zero-Mem introduces zero-token memory operations: no step outside final question answering invokes an LLM or consumes LLM input or output tokens; encoder computation is accounted for separately. Zero-Mem preserves original interaction traces as its source of record. It organizes the traces in two complementary ways. An entity--context graph exposes connections across interactions, while a temporal hierarchy preserves conversational locality and session state. For each query, Zero-Mem weighs the two views, retrieves from both, and follows their structure to recover supporting relations or surrounding context. Deterministic calibration first discards conflicting evidence and then keeps the reader's answer grounded in the retrieved traces. Only the final-QA reader invokes an LLM. Across long-memory and long-context question-answering benchmarks, Zero-Mem achieves competitive performance while eliminating LLM calls and LLM-token consumption from memory operations. With the same final-QA reader and context budget, it reduces memory-operation time cost by 57.6\% relative to the fastest compared baseline. Ablations support the contribution of the two views and their query-dependent coordination. Overall, the results show that structured agent memory need not generate an intermediate representation of the past. After peer review, the code and implementation details will be available at blue{https://github.com/TheMoon0815/Zero-mem}.

Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for decision-making. At the same time, useful experience gained from tasks is often lost across episodes. We argue that long-horizon performance is determined not by context length, but by how much decision-relevant information is maintained within a finite context budget. We present GenericAgent (GA), a general-purpose, self-evolving LLM agent system built around a single principle: context information density maximization. GA implements this through four closely connected components: a minimal atomic tool set that keeps the interface simple, a hierarchical on-demand memory that only shows a small high-level view by default, a self-evolution mechanism that turns verified past trajectories into reusable SOPs and executable code, and a context truncation and compression layer that maintains information density during long executions. Across task completion, tool use efficiency, memory effectiveness, self-evolution, and web browsing, GA consistently outperforms leading agent systems while using significantly fewer tokens and interactions, and it continues to evolve over time. Project: https://github.com/lsdefine/GenericAgent

Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by attending to a subset of key-value cache entries, yet most methods allocate a fixed context budget throughout decoding despite highly non-uniform token-level contextual demands. To address this issue, we propose Uncertainty-Triggered Adaptive Context Allocation (UT-ACA), an inference-time framework that dynamically adjusts the context window based on token-wise uncertainty. UT-ACA learns an uncertainty detector that combines semantic embeddings with logit-based confidence while accounting for uncertainty accumulation across decoding steps. When insufficient evidence is indicated, UT-ACA selectively rolls back, expands the context window, and regenerates the token with additional support. Experiments show that UT-ACA substantially reduces average context usage while preserving generation quality in long-context settings.

Large language models with long context windows can answer complex questions directly from full-length academic, technical, and policy documents, but passing entire documents is often costly, slow, and can degrade answer quality while increasing the risk of unnecessary data leakage. This paper targets the common setting of answering many heterogeneous questions over long document(s), where fixed position heuristics and standard retrieval-augmented generation (RAG) can fail due to document structure variability and weak query-chunk semantic similarity, which often requires task- and domain-specific tuning of embedding retrievers. We propose {Selective Attention-Guided Extraction} (\ourmethod), a training-free, plug-and-play context reduction framework that uses a lightweight local LLM to perform a single prefilling pass and convert language model attention signals into a query-specific relevance heatmap at configurable granularities. \ourmethod\ further introduces differential attention strategies to better isolate question-relevant evidence, then selects the top-scoring units under a user-defined token budget and forwards only this reduced context to a downstream LLM for answer generation. \ourmethod\ surpasses traditional reduction techniques across multiple long-document QA benchmarks, notably securing a top-4 rank on QuALITY-hard while constrained to a 10\% context budget. This enables a 90\% reduction in tokens with competitive accuracy, without the need for model fine-tuning or complex calibration.

Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For current multimodal LLMs: even with million-token context windows, frame budgets cover only tens of minutes of densely sampled video, and most evidence is discarded before inference begins. Memory-augmented and agentic approaches help with scale, but their retrieval remains fragmented across modalities and lacks long-range narrative summaries that span days or weeks. We propose MAGIC-Video, a training-free framework built around a multimodal memory graph with interleaved narrative chain: the graph unifies episodic, semantic, and visual content through six typed edges and supports cross-modal retrieval, while the chain distils long-horizon entity biographies and recurring activity events. At inference time, an agentic loop interleaves graph retrieval with narrative fact injection, covering both the modality and time dimensions of ultra-long video in a single retrieval pipeline. On EgoLifeQA, Ego-R1 and MM-Lifelong, MAGIC-Video consistently outperforms strong general-purpose, long-video, and agentic baselines, with gains of 10.1, 7.4, and 5.9 points over the prior best agentic system on each benchmark. Code is available at https://github.com/lijiazheng0917/MAGIC-video.

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress intermediate thoughts into compact semantic representations. However, static compression often struggles with complex reasoning where the irreversible loss of intermediate details can lead to logical bottlenecks. To address this, we evolve the framework into LightThinker++, introducing Explicit Adaptive Memory Management. This paradigm shifts to behavioral-level management by incorporating explicit memory primitives, supported by a specialized trajectory synthesis pipeline to train purposeful memory scheduling. Extensive experiments demonstrate the framework's versatility across three dimensions. (1) LightThinker reduces peak token usage by 70% and inference time by 26% with minimal accuracy loss. (2) In standard reasoning, LightThinker++ slashes peak token usage by 69.9% while yielding a +2.42% accuracy gain under the same context budget for maximum performance. (3) Most notably, in long-horizon agentic tasks, it maintains a stable footprint beyond 80 rounds (a 60%-70% reduction), achieving an average performance gain of 14.8% across different complex scenarios. Overall, our work provides a scalable direction for sustaining deep LLM reasoning over extended horizons with minimal overhead.

Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be encoded in growing input contexts. The resulting degraded reasoning quality, increased inference cost, and higher latency necessitate efficient working memory mechanisms. However, existing approaches either rely on lossy compression or similarity-based retrieval, which often fail to capture temporal structure and causal dependencies required for multi-step agentic tasks. In this work, we present HORMA, a Hierarchical Organize-and-Retrieve Memory Agent that organizes experience into a file-system-like hierarchical structure, where summarized entities are linked to the corresponding raw trajectories, enabling efficient access without losing detailed information. HORMA decomposes working memory into two stages: structured memory construction and navigation-based retrieval. The construction module iteratively refines how experiences are structured by distinguishing between failures caused by missing information and those caused by misleading or overloaded context. The navigation module retrieves task-relevant context by traversing the hierarchy using a lightweight agent trained with reinforcement learning to select minimal yet sufficient context, thereby reducing latency along the critical execution path. Across ALFWorld, LoCoMo, and LongMemEval, HORMA improves task performance under constrained context budgets while requiring at most 22.17% of the baseline token usage in long conversation tasks. Compared to existing methods, it consistently achieves better efficiency-performance trade-offs and generalizes effectively to unseen tasks.

We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a session accumulates history, CWL keeps the context within budget through graduated, semantically-aware eviction: the agent annotates its trajectory as typed, dependency-linked episodes as work proceeds, and a deterministic, LLM-free policy evicts content in priority order within that structure when a token budget is exceeded. CWL preserves user turns and the exploratory context the agent is actively reasoning over, while aggressively shedding action episodes whose effects are already persisted in the environment, keeping active context near a stable ceiling that also avoids the performance degradation associated with very large prompts. Compared to summarization-based compaction, CWL avoids four well-known limitations: unpredictable lossiness, destruction of causal structure, blocking model cost, and compression-induced hallucination. Compared to recency truncation, CWL is semantically aware: it drops the oldest-and-most-recoverable content according to the dependency graph rather than oldest-in-time regardless of relevance. We describe the annotation protocol, the episode graph, the eviction policy, and the token-accounting loop, and evaluate CWL on long-horizon agentic benchmarks: a single agent session completing 89 sequential tasks across 80 million tokens with no measurable degradation in task accuracy relative to per-task isolated sessions

Computer-use agents (CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual tokens. As interaction trajectories grow, the token cost increases rapidly, limiting the amount of history that can be incorporated under fixed context and compute budgets. This has resulted in no or very limited improvement in the performance when using history unlike other domains. We address this inefficiency by introducing ReVision, which is used to train multimodal language models on trajectories where redundant visual patches are removed using a learned patch selector that compares patch representations across consecutive screenshots while preserving spatial structure required by the model. Across three benchmarks, OSWorld, WebTailBench, and AgentNetBench, when processing trajectories with 5 history screenshots using Qwen2.5-VL-7B, ReVision reduces token usage by 46% on average while improving success rate by 3% over the no drop baseline. This establishes a clear efficiency gain, enabling agents to process longer trajectories with fewer tokens. With this improved efficiency, we revisit the role of history in CUAs and find that performance continues to improve as more past observations are incorporated when redundancy is removed.

Key-value (KV) caching is widely used to accelerate transformer inference, but its memory cost grows linearly with input length, limiting long-context deployment. Existing token eviction methods reduce memory by discarding less important tokens, which can be viewed as a coarse form of dimensionality reduction that assigns each token either zero or full dimension. We propose MixedDimKV, a mixed-dimension KV cache compression method that allocates dimensions to tokens at a more granular level, and MixedDimKV-H, which further integrates head-level importance information. Experiments on long-context benchmarks show that MixedDimKV outperforms prior KV cache compression methods that do not rely on head-level importance profiling. When equipped with the same head-level importance information, MixedDimKV-H consistently outperforms HeadKV. Notably, our approach achieves comparable performance to full attention on LongBench with only 6.25% of the KV cache. Furthermore, in the Needle-in-a-Haystack test, our solution maintains 100% accuracy at a 50K context length while using as little as 0.26% of the cache.

Retrieval-augmented generation (RAG) under a fixed reader-context budget forces a selection problem: of the evidence retrieved, only a fraction can be shown to the reader. We argue that document recall -- the standard retrieval metric -- is the wrong quantity to optimize in this regime, and we make two contributions. First, as a general contribution, we introduce answer-in-context, a diagnostic that measures whether a gold answer survives as a contiguous span in the packed reader context (not the retrieved set). It predicts answer F1 better than recall (r=0.39-0.55 vs. about 0.31), separates answer quality roughly five-fold (0.60 vs. 0.12 on HotpotQA), and carries information beyond retrieval: it adds Delta R squared=0.17 over recall and shows a 4.6x EM gap even among questions where all gold was retrieved. We also confirm it interventionally: on 2WikiMultiHopQA a packing change that raises coverage but not answer-in-context yields no accuracy gain. Second, as a conditional contribution, we cast reader-context construction as budgeted monotone submodular maximization and build a packer that jointly optimizes relevance, query coverage, representativeness, and diversity. On HotpotQA with a 160-token budget and a 3B reader it beats a strong focused heuristic, MMR, and naive packing -- by up to +5.1 F1 at equal-or-lower token cost, across three seeds. Crucially, we map the scope of this win honestly: it requires the conjunction of (i) multi-hop complementary structure, (ii) retrieval that surfaces the evidence, (iii) a binding but not extreme budget, and (iv) a reader weak enough that evidence density, not reading capacity, is the bottleneck. A quantization-controlled reader-scale ladder (3B to 7B to 14B) shows the edge over the heuristic is absorbed by 7B and significantly reverses by 14B, while the diagnostic explains every boundary with a single variable.

A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment. The gap is especially important for AI agents, whose observations, tool outputs, documents, and prior decisions accumulate over long trajectories. LongStraw is an architecture-aware execution stack for million-token RL post-training under a fixed GPU budget, instantiated with Group Relative Policy Optimization (GRPO). It evaluates the shared prompt without autograd, retains only model-specific state needed by later tokens, and replays short response branches one at a time, reducing the live training graph at the cost of additional replay time. We implement it for the hybrid recurrent and full-attention Qwen3.6-27B and the compressed-attention mixture-of-experts GLM-5.2. On eight H20 GPUs, LongStraw completes grouped Qwen scoring and response backward at 2.1M positions for groups of 2 and 8; increasing the group size adds only 0.21 GB of peak allocated memory, while a separate stress test reaches 4.46M positions. On 32 H20 GPUs, we validate the end-to-end LongStraw execution path for a 2.1M-token prompt across all 78 layers of GLM-5.2. These experiments establish execution capacity rather than complete training correctness because the captured prompt state is detached and some distributed forward and gradient composition paths remain incomplete.

The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction methods reduce this cost but typically degrade performance relative to full-cache inference. Our key insight is that full-cache attention is not always optimal: in long contexts, irrelevant tokens can dilute attention away from useful evidence, so selective, learnable eviction can improve generation rather than merely approximate the full cache. We introduce a global retention-based KV eviction method that learns each token's future utility under a unified memory budget. Lightweight retention gates assign utility scores to cached KV entries, and a shared final scoring projection calibrates these scores across all layers and heads. This enables a single global eviction policy in which tokens from different layers, heads, and modalities compete directly for cache capacity. We further provide theoretical analysis showing that preferentially retaining useful tokens reduces attention dilution, and we justify geometric retention as a query-agnostic proxy for future utility. Across diverse long-context language and vision-language reasoning, and multi-turn dialogue benchmarks, our method substantially reduces KV memory while matching or surpassing full-cache inference. These results suggest that learned, globally calibrated KV eviction is not only a compression technique, but also a mechanism for improving long-context reasoning.

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference latency, yet still suffer from inherently insufficient structure optimization, outdated selection criteria, and redundancy interference, resulting in suboptimal speed-accuracy trade-off. To address these issues, we propose a novel training-free framework dubbed Self-Predictive Token Skipping (SPTS), for efficient long-context LLM inference. Specifically, motivated by probing the influence of target layers prior to skipping, we design two selective token skipping strategies for typical structures, including Partial Attention Probing (PAP) for multi-head attention and Low-rank Transformation Probing (LTP) for feed forward network. The former selects informative tokens via partial forward attention computation, while the latter constructs a low-rank proxy network to predict token transformations. In addition, a Multi-Stage Delayed Pruning (MSDP) strategy reallocates skipping budgets and progressively removes redundant tokens across layers. Extensive experiments display the effectiveness of our method, achieving up to 2.46times and 2.29times speedups for prefilling and end-to-end generation, respectively, while maintaining state-of-the-art accuracy. We will release the source code upon acceptance.

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a transient memory structure that grows linearly with sequence length and batch size, quickly dominating GPU memory usage. Existing memory reduction techniques, including eviction and quantization, often rely on static heuristics and suffer from degraded quality under tight budgets. In this paper, we propose ARKV, a lightweight and adaptive framework that dynamically allocates precision levels to cached tokens based on per-layer attention dynamics and token-level importance. During a short prefill phase, ARKV estimates the original quantization (OQ) ratio of each layer by computing statistical scores such as attention entropy, variance and kurtosis. During decoding, tokens are assigned to one of three states, Original (full precision), Quantization (low precision), or Eviction, according to a fast heavy-hitter scoring strategy. Our experiments on LLaMA3 and Qwen3 models across diverse long- and short-context tasks demonstrate that ARKV preserves ~97% of baseline accuracy on long-context benchmarks while reducing KV memory usage by 4x, with minimal throughput loss. On short-context tasks, ARKV matches full-precision baselines; on GSM8K math reasoning, it significantly outperforms uniform quantization. These results highlight the practical viability of ARKV for scalable LLM deployment, offering fine-grained, data-driven memory control without retraining or architectural modifications. The source code and artifacts can be found in: https://github.com/Large-scale-Sustainable-Computing-LSC/ARKV

We present Harmonic, a hierarchical state space model (SSM) for language modeling. The architecture stacks three recurrent levels at progressively slower timescales; each level receives the prediction error of the level below as input, rather than its raw hidden state. On enwiki8 with equal token budgets, Harmonic outperforms a comparable Transformer (28M params) by +1.4% at 1K tokens, +6.7% at 8K tokens, and +11.4% at 32K tokens (bpt, lower is better). It also outperforms Mamba at every tested length by 0.7--1.8%. At 64K tokens, both Mamba and Transformer run out of memory on an 80GB H100; Harmonic trains successfully, reaching 6.169 bpt. Results replicate on WikiText-103 (H-TF gap +1.7% to +7.2% across 1K--32K). At 1B parameter scale, replacing all attention layers in TinyLlama 1.1B with HarmonicBlock eliminates the RoPE positional encoding limit: the resulting Hallamonic model maintains stable loss across sequence lengths 1K--8K on two independent clean benchmarks (Lambada and fineweb-edu held-out), while TinyLlama degrades catastrophically past its 2K-token RoPE limit (gap: +9.4 bpt at seq=8K on Lambada). Compute is O(L) per forward pass vs. O(L^2) for attention. Logs: https://github.com/Omibranch/harmonic-logs.

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As sequence lengths increase, the number of Key-Value (KV) pairs in LLMs escalates, creating a significant efficiency bottleneck. In this paper, we propose a new KV cache optimization paradigm called LaCache, a training-free method for efficient and accurate generative inference of LLMs. LaCache enables LLMs to simultaneously address both of the critical challenges in long-range modeling: robust long-range capabilities and continuous generation without running out-of-memory (OOM). Specifically, LaCache integrates two key innovations: (1) a ladder-shaped KV cache pattern that stores KV pairs not only sequentially (left-to-right within each layer) but also across layers (from shallow to deep), providing an extended span for capturing long-range dependencies under a fixed storage budget, thereby boosting long-range capabilities; and (2) an iterative compaction mechanism that progressively compresses older caches, freeing up space for new tokens within a fixed cache size. This token distance-based dynamic compression enables more effective continuous generation under constrained cache budgets. Experiments across various tasks, benchmarks, and LLM models consistently validate LaCache's effectiveness in enhancing LLMs' long-range capabilities. Our code is available at https://github.com/GATECH-EIC/LaCache.

Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show that this assumption often breaks down: for the same query, audio and video relevance often peaks at different moments. This cross-modal salience mismatch makes unidirectional guidance prone to discarding answer-critical cues under aggressive compression. We propose OmniScope, a training-free token compression framework that uses the query as a shared semantic anchor while estimating relevance separately for audio and video. OmniScope allocates modality-specific token budgets, prunes visual tokens with an anchor-delta strategy that preserves both global context and temporal changes, and merges audio tokens within each second to reduce redundancy while maintaining temporal continuity. Across four audio-video benchmarks and two Qwen2.5-Omni model scales, OmniScope achieves the best average accuracy across all compression settings. At 25% overall token retention, it delivers up to 3.53x prefill speedup and more than 15% GPU memory reduction, with only a 0.35-point drop in average accuracy. These results suggest a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates. The code is available at https://github.com/MAC-AutoML/OmniScope.

The primary way of building AI applications is shifting from training specialist models to prompting generalist models. A common practice for prompting generalist models, often referred to as in-context learning, is to append a few examples (demonstrations) to the prompt to help the model better understand the task. While effective, in-context learning can be inefficient because it makes the input prompt much longer, consuming valuable space in the context window and leading to larger computational costs. In this paper, we propose DynaICL, a recipe for efficient prompting with black-box generalist models that dynamically allocate in-context examples according to the input complexity and the computational budget. To achieve this, we train a meta controller that predicts the number of in-context examples suitable for the generalist model to make a good prediction based on the performance-efficiency trade-off for a specific input. We then dynamically allocate the number of demonstrations for an input according to predictions from the meta controller and the given computation budget. Experimental results show that dynamic example allocation helps achieve a better performance-efficiency trade-off in two practical settings where computational resources or the required performance is constrained. Specifically, DynaICL saves up to 46% token budget compared to the common practice that allocates the same number of in-context examples to each input. We also find that a meta controller trained on a certain backbone model and tasks can successfully generalize to unseen models and tasks.

Large language models (LLMs) now support context windows of hundreds of thousands to millions of tokens, enabling applications such as long-document summarization, large-scale code synthesis, multi-document question answering and persistent multi-turn dialogue. However, such extended contexts exacerbate the quadratic cost of self-attention, leading to severe latency in autoregressive decoding. Existing sparse attention methods alleviate these costs but rely on heuristic patterns that struggle to recall critical key-value (KV) pairs for each query, resulting in accuracy degradation. We introduce Adamas, a lightweight yet highly accurate sparse attention mechanism designed for long-context inference. Adamas applies the Hadamard transform, bucketization and 2-bit compression to produce compact representations, and leverages Manhattan-distance estimation for efficient top-k selections. Experiments show that Adamas matches the accuracy of full attention with only a 64-token budget, achieves near-lossless performance at 128, and supports up to 8x higher sparsity than prior state-of-the-art (SOTA) methods while delivering up to 4.4x self-attention and 1.5x end-to-end speedups on 32K-length sequences. Remarkably, Adamas attains comparable or even lower perplexity than full attention, underscoring its effectiveness in maintaining accuracy under aggressive sparsity.

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and decoding stages. Recent works that compress KV caches with prefill acceleration reduce this cost but inadvertently tie the prefill compute reduction to the decoding KV budget. This coupling arises from overlooking the layer-dependent variation of critical context, often leading to accuracy degradation. To address this issue, we introduce FastKV, a KV cache compression framework designed to reduce latency in both prefill and decoding by leveraging the stabilization of token importance in later layers. FastKV performs full-context computation until a Token-Selective Propagation (TSP) layer, which forwards only the most informative tokens to subsequent layers. From these propagated tokens, FastKV independently selects salient KV entries for caching, thereby decoupling KV budget from the prefill compute reduction based on the TSP decision. This independent control of the TSP rate and KV retention rate enables flexible optimization of efficiency and accuracy. Experimental results show that FastKV achieves speedups of up to 1.82times in prefill and 2.87times in decoding compared to the full-context baseline, while matching the accuracy of the baselines that only accelerate the decoding stage. Our code is available at https://github.com/dongwonjo/FastKV.

Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approaches preserve either the agent's trajectory, passive access to raw material, or task-level strategies. None of them preserves what we argue is most needed for repeated same-context workloads: reusable orientation knowledge (e.g., what the context contains, how it is organized, and which entities, constants, and schemas have historically been useful) about the recurring context itself. We introduce PEEK, a system that caches and maintains this orientation knowledge as a context map: a small, constant-sized artifact in the agent's prompt that gives it a persistent peek into the external context. The map is maintained by a programmable cache policy with three modules: a Distiller that extracts transferable knowledge from inference-time signals, a Cartographer that translates it into structured edits, and a priority-based Evictor that enforces a fixed token budget. On long-context reasoning and information aggregation, PEEK improves over strong baselines by 6.3-34.0% while using 93-145 fewer iterations and incurring 1.7-5.8x lower cost than the state-of-the-art prompt-learning framework, ACE. On context learning, PEEK improves solving rate and rubric accuracy by 6.0-14.0% and 7.8-12.1%, respectively, at 1.4x lower cost than ACE. These gains generalize across LMs and agent architectures, including OpenAI Codex, a production-grade coding agent. Together, these results show that a context map helps long-context LLM agents interact with recurring external contexts more accurately and efficiently.

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-attention mechanism, which enables modeling of long-range dependencies. However, the quadratic complexity of self-attention with respect to sequence length poses significant computational and memory challenges, especially as sequence length extends to extremes. While various sparse attention and KV cache compression methods have been proposed to improve efficiency, they often suffer from limitations such as reliance on fixed patterns, inability to handle both prefilling and decoding stages, or the requirement for additional training. In this paper, we propose Training-free Context-adaptive Attention (TCA-Attention), a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference. Our method consists of two lightweight phases: i) an offline calibration phase that determines head-specific sparsity budgets via a single forward pass, and ii) an online token selection phase that adaptively retains core context tokens using a lightweight redundancy metric. TCA-Attention provides a unified solution that accelerates both prefilling and decoding while reducing KV cache memory footprint, without requiring parameter updates or architectural changes. Theoretical analysis shows that our approach maintains bounded approximation error. Extensive experiments demonstrate that TCA-Attention achieves a 2.8times speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention across various benchmarks, offering a practical plug-and-play solution for efficient long-context inference.

Creative image editing tools, such as Photoshop's Remove or Generative Fill buttons, are central to everyday customer use and account for a major share of traffic in Photoshop and Lightroom. However, current generative AI models face significant latency challenges, which become even more pronounced when transitioning from convolution-based U-Nets to Diffusion Transformers (DiTs). In our evaluation on hundreds of representative image editing samples spanning a wide range of mask ratios, the DiT module alone accounts for an average of 73% of the total model latency, even after being distilled from 50 timesteps down to 8 timesteps. To tackle this challenge, we propose HiLo-Token, an input-adaptive token compression framework that allocates more token budget to high-frequency, rich-context regions while assigning fewer tokens to low-frequency areas. Specifically, for the editing region specified by the user mask, we retain all tokens within a dilated mask to preserve strong locality and contextual relevance. Outside the editing region, we introduce a simple yet effective high-frequency token selection strategy based on spatial frequency to capture important local details, while using tokens from a 16x downsampled image to represent low-frequency components and preserve the blurry but global structure. Extensive experiments on production-level evaluation data validate the effectiveness of the proposed method, achieving 3.13x, 2.59x, and 1.67x DiT speedups on A100-80GB for image editing tasks across small, medium, and large mask ratio categories with average ratios of 6.38%, 15.92%, and 35.36%, respectively, without any regression in generation quality.

Despite their powerful capabilities, Multimodal Large Language Models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens. Recent studies have explored token pruning to alleviate this problem, which typically uses text-vision cross-attention or [CLS] attention to assess and discard redundant visual tokens. In this work, we identify a critical limitation of such attention-first pruning approaches, i.e., they tend to preserve semantically similar tokens, resulting in pronounced performance drops under high pruning ratios. To this end, we propose {HoloV}, a simple yet effective, plug-and-play visual token pruning framework for efficient inference. Distinct from previous attention-first schemes, HoloV rethinks token retention from a holistic perspective. By adaptively distributing the pruning budget across different spatial crops, HoloV ensures that the retained tokens capture the global visual context rather than isolated salient features. This strategy minimizes representational collapse and maintains task-relevant information even under aggressive pruning. Experimental results demonstrate that our HoloV achieves superior performance across various tasks, MLLM architectures, and pruning ratios compared to SOTA methods. For instance, LLaVA1.5 equipped with HoloV preserves 95.8\% of the original performance after pruning 88.9\% of visual tokens, achieving superior efficiency-accuracy trade-offs.

Large language models (LLMs) have achieved remarkable success in many natural language processing (NLP) tasks. To achieve more accurate output, the prompts used to drive LLMs have become increasingly longer, which incurs higher computational costs. To address this prompt inflation problem, prompt compression has been proposed. However, most existing methods require training a small auxiliary model for compression, incurring a significant amount of additional computation. To avoid this, we propose a two-stage, training-free approach, called Dual-Stage Progressive Compression (DSPC). In the coarse-grained stage, semantic-related sentence filtering removes sentences with low semantic value based on TF-IDF. In the fine-grained stage, token importance is assessed using attention contribution, cross-model loss difference, and positional importance, enabling the pruning of low-utility tokens while preserving semantics. We validate DSPC on LLaMA-3.1-8B-Instruct and GPT-3.5-Turbo under a constrained token budget and observe consistent improvements. For instance, in the FewShot task of the Longbench dataset, DSPC achieves a performance of 49.17 by using only 3x fewer tokens, outperforming the best state-of-the-art baseline LongLLMLingua by 7.76.

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet practical training recipes remain insufficiently explored, particularly for designing and balancing long-context data mixtures. In this work, we present a systematic study of long-context continued pre-training for LVLMs, extending a 7B model from 32K to 128K context with extensive ablations on long-document data. We first show that long-document VQA is substantially more effective than OCR transcription. Building on this observation, our ablations further yield three key findings: i) for sequence-length distribution, balanced data outperforms target-length-focused data (e.g., 128K), suggesting that long-context ability requires generalizable key-information retrieval across various lengths and positions; ii) retrieval remains the primary bottleneck, favoring retrieval-heavy mixtures with modest reasoning data for task diversity; and iii) pure long-document VQA largely preserves short-context capabilities, suggesting that instruction-formatted long data reduces the need for short-data mixing. Based on these findings, we introduce MMProLong, obtained by long-context continued pre-training from Qwen2.5-VL-7B with only a 5B-token budget. MMProLong improves long-document VQA scores by 7.1% and maintains strong performance at 256K and 512K contexts beyond its 128K training window, without additional training. It further generalizes to webpage-based multimodal needle retrieval, long-context vision-text compression, and long-video understanding without task-specific supervision. Overall, our study establishes a practical LongPT recipe and an empirical foundation for advancing long-context vision-language models.

Vision-language models (VLMs) often generate massive visual tokens that greatly increase inference latency and memory footprint; while training-free token pruning offers a practical remedy, existing methods still struggle to balance local evidence and global context under aggressive compression. We propose Focus-Scan-Refine (FSR), a human-inspired, plug-and-play pruning framework that mimics how humans answer visual questions: focus on key evidence, then scan globally if needed, and refine the scanned context by aggregating relevant details. FSR first focuses on key evidence by combining visual importance with instruction relevance, avoiding the bias toward visually salient but query-irrelevant regions. It then scans for complementary context conditioned on the focused set, selecting tokens that are most different from the focused evidence. Finally, FSR refines the scanned context by aggregating nearby informative tokens into the scan anchors via similarity-based assignment and score-weighted merging, without increasing the token budget. Extensive experiments across multiple VLM backbones and vision-language benchmarks show that FSR consistently improves the accuracy-efficiency trade-off over existing state-of-the-art pruning methods. The source codes can be found at https://github.com/ILOT-code/FSR.

As real-world applications increasingly require processing inputs of 100k+ tokens, the gap between context length and inference efficiency has become a critical bottleneck. Context compression offers a way to reduce prefill costs while preserving task accuracy. However, existing training-free attention-based methods leave substantial gaps in demanding long-context tasks such as code reasoning. We present LongAttnComp, a long-context adaptation of AttnComp that fine-tunes a lightweight cross-attention scoring layer and introduces tokenlevel chunking, a token-budget top-p algorithm, positional reordering, and a formatagnostic query parser. We further design a two-stage fine-tuning recipe for the compressor: Stage 1 builds a general retrieval foundation from NIAH-style data, and Stage 2 extends it with multi-hop and reasoning data for broader long-context task coverage. On InfiniteBench Code-Debug, LongAttnComp matches or exceeds full-context accuracy, substantially outperforms training-free baselines, and transfers across four target models from three families. On LongBench v2, the two-stage recipe largely closes the Stage 1 gap on multi-document reasoning while preserving Code-Debug performance.

Multi-agent large language model (LLM) systems have shown strong potential in complex reasoning and collaborative decision-making tasks. However, most existing coordination schemes rely on static or full-context routing strategies, which lead to excessive token consumption, redundant memory exposure, and limited adaptability across interaction rounds. We introduce RCR-Router, a modular and role-aware context routing framework designed to enable efficient, adaptive collaboration in multi-agent LLMs. To our knowledge, this is the first routing approach that dynamically selects semantically relevant memory subsets for each agent based on its role and task stage, while adhering to a strict token budget. A lightweight scoring policy guides memory selection, and agent outputs are iteratively integrated into a shared memory store to facilitate progressive context refinement. To better evaluate model behavior, we further propose an Answer Quality Score metric that captures LLM-generated explanations beyond standard QA accuracy. Experiments on three multi-hop QA benchmarks -- HotPotQA, MuSiQue, and 2WikiMultihop -- demonstrate that RCR-Router reduces token usage (up to 30%) while improving or maintaining answer quality. These results highlight the importance of structured memory routing and output-aware evaluation in advancing scalable multi-agent LLM systems.

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks. However, their deployment in long context scenarios remains hindered by computational inefficiency and information redundancy. Context compression methods address these challenges by significantly reducing input length and eliminating redundancy. We propose COMI, a coarse-to-fine adaptive context compression framework that jointly optimizes for semantic relevance and diversity under high compression rates. We introduce Marginal Information Gain (MIG), a metric defined as the relevance of a unit to the input query minus its semantic redundancy with other units, guiding the compression process to prioritize information that is both relevant and low redundant. The framework operates in two stages: (1) Coarse-Grained Group Reallocation, where the context is partitioned into groups and dynamically assigned compression rates based on inter-group MIG, ensuring compression budgets align with information value distribution; and (2) Fine-Grained Token Merging, where tokens within each group are fused via an intra-group MIG-based weighting mechanism, thereby preserving key semantics while avoiding the accumulation of redundancy. Extensive experiments across question-answering (e.g., NaturalQuestions, 2WikiMQA, HotpotQA and NarrativeQA), summarization (e.g., MultiNews) with various backbones (e.g., LLaMA-2-7B, Qwen2-7B) show that COMI outperforms existing baselines by a large margin, e.g., approximately 25-point Exact Match (EM) improvement under 32x compression constraint with Qwen2-7B on NaturalQuestions.

Large language model (LLM) contexts are typically constructed using retrieval-augmented generation (RAG), which involves ranking and selecting the top-k passages. The approach causes fragmentation in information graphs in document structures, over-retrieval, and duplication of content alongside insufficient query context, including 2nd and 3rd order facets. In this paper, a structure-informed and diversity-constrained context bubble construction framework is proposed that assembles coherent, citable bundles of spans under a strict token budget. The method preserves and exploits inherent document structure by organising multi-granular spans (e.g., sections and rows) and using task-conditioned structural priors to guide retrieval. Starting from high-relevance anchor spans, a context bubble is constructed through constrained selection that balances query relevance, marginal coverage, and redundancy penalties. It will explicitly constrain diversity and budget, producing compact and informative context sets, unlike top-k retrieval. Moreover, a full retrieval is emitted that traces the scoring and selection choices of the records, thus providing auditability and deterministic tuning. Experiments on enterprise documents demonstrate the efficiency of context bubble as it significantly reduces redundant context, is better able to cover secondary facets and has a better answer quality and citation faithfulness within a limited context window. Ablation studies demonstrate that both structural priors as well as diversity constraint selection are necessary; removing either component results in a decline in coverage and an increase in redundant or incomplete context.

Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query. Existing pruning methods often combine query relevance and token diversity, yet these objectives can conflict under aggressive compression: relevance-driven selection may overconcentrate the budget on correlated local evidence, while diversity-driven selection may suppress indispensable tokens or retain distinct but uninformative regions. We introduce AnchorPrune, a training-free framework that first constructs a protected relevance anchor and then expands it with complementary visual context. AnchorPrune adaptively determines the anchor size from the novelty profile of relevance-ranked tokens, preserving a compact set of query-critical evidence, and allocates the remaining budget through importance-weighted novelty to recover informative, non-redundant context relative to the anchor. This ordered design prevents contextual expansion from displacing indispensable query cues while improving overall visual coverage. AnchorPrune is lightweight, architecture-aware, and requires neither retraining nor model modification. Across image and video vision-language models and benchmarks, it consistently improves the accuracy-efficiency trade-off over training-free baselines, particularly under severe compression. On LLaVA-NeXT-7B, AnchorPrune preserves 97.6% of full-token performance using only 160 of 2,880 visual tokens. These results establish relevance-anchored contextual expansion as an effective principle for efficient multimodal inference. Code is available at https://github.com/MULTI-cau/AnchorPrune.

Recent advancements in LLM pretraining have featured ever-expanding context windows to process longer sequences. However, our pilot study reveals that models pretrained with shorter context windows consistently outperform their long-context counterparts under a fixed token budget. This finding motivates us to explore an optimal context window scheduling strategy to better balance long-context capability with pretraining efficiency. To this end, we propose SkyLadder, a simple yet effective approach that implements a short-to-long context window transition. SkyLadder preserves strong standard benchmark performance, while matching or exceeding baseline results on long context tasks. Through extensive experiments, we pre-train 1B-parameter models (up to 32K context) and 3B-parameter models (8K context) on 100B tokens, demonstrating that SkyLadder yields consistent gains of up to 3.7% on common benchmarks, while achieving up to 22% faster training speeds compared to baselines. The code is at https://github.com/sail-sg/SkyLadder.

Code generation under long contexts is becoming increasingly critical as Large Language Models (LLMs) are required to reason over extensive information in the codebase. While recent advances enable code LLMs to process long inputs, high API costs and generation latency remain substantial bottlenecks. Existing context pruning techniques, such as LLMLingua, achieve promising results for general text but overlook code-specific structures and dependencies, leading to suboptimal performance in programming tasks. In this paper, we propose LongCodeZip, a novel plug-and-play code compression framework designed specifically for code LLMs. LongCodeZip employs a dual-stage strategy: (1) coarse-grained compression, which identifies and ranks function-level chunks using conditional perplexity with respect to the instruction, retaining only the most relevant functions; and (2) fine-grained compression, which segments retained functions into blocks based on perplexity and selects an optimal subset under an adaptive token budget to maximize relevance. Evaluations across multiple tasks, including code completion, summarization, and question answering, show that LongCodeZip consistently outperforms baseline methods, achieving up to a 5.6x compression ratio without degrading task performance. By effectively reducing context size while preserving essential information, LongCodeZip enables LLMs to better scale to real-world, large-scale code scenarios, advancing the efficiency and capability of code intelligence applications.

Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeated High Bandwidth Memory (HBM) streaming rather than arithmetic. Existing methods such as eviction, windowing, quantization, and offloading reduce footprint, but often leave the critical-path bottleneck only partially addressed, especially when compressed states must still be reconstructed into dense vectors during decoding. We present Spherical KV, a long-context inference method that treats KV allocation as a rate-distortion problem grounded in attention geometry for efficient decoding. The method is built on two ideas: (i) represent directional information cheaply in the decode hot loop, and (ii) allocate retention and precision according to estimated future utility. Its first component, Angle-Domain Attention (ADA), stores keys in a spherical parameterization consisting of a scalar radius and compact angle codes, and computes attention logits directly from these codes without reconstructing dense keys. This preserves a paged, block-local, fusion-friendly decode path and directly targets HBM traffic in realistic serving settings. Its second component, Rate-Distortion Retention (RDR), jointly chooses keep/drop decisions and precision tiers per token and head under a fixed budget, producing tier-homogeneous pages with lightweight metadata and coalesced reads. Together, ADA and RDR provide a deployment-oriented mechanism for reducing KV residency while preserving decode efficiency.

As model capabilities advance, research has increasingly shifted toward long-horizon, multi-turn terminal-centric agentic tasks, where raw environment feedback is often preserved in the interaction history to support future decisions. However, repeatedly retaining such feedback introduces substantial redundancy and causes cumulative token cost to grow quadratically with the number of steps, hindering long-horizon reasoning. Although observation compression can mitigate this issue, the heterogeneity of terminal environments makes heuristic-based or fixed-prompt methods difficult to generalize. We propose TACO, a plug-and-play, self-evolving Terminal Agent Compression framework that automatically discovers and refines compression rules from interaction trajectories for existing terminal agents. Experiments on TerminalBench (TB 1.0 and TB 2.0) and four additional terminal-related benchmarks (i.e., SWE-Bench Lite, CompileBench, DevEval, and CRUST-Bench) show that TACO consistently improves performance across mainstream agent frameworks and strong backbone models. With MiniMax-2.5, it improves performance on most benchmarks while reducing token overhead by around 10%. On TerminalBench, it brings consistent gains of 1%-4% across strong agentic models, and further improves accuracy by around 2%-3% under the same token budget. These results demonstrate the effectiveness and generalization of self-evolving, task-aware compression for terminal agents.

Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences. However, they still struggle with long-horizon tasks, such as tracking a user's extensive history of conversations or activities. Existing memory mechanisms often fail to capture evolving behaviors, and RAG paradigms are trapped by a quality-efficiency tradeoff. Meanwhile, parametric adaptation is bottlenecked by train-inference gap due to the scarcity of labeled data. To enhance the long-horizon capabilities of PLLMs, we introduce TSUBASA, a two-pronged approach designed to improve memory writing via dynamic memory evolution, and memory reading via self-learning with a context distillation objective to internalize user experiences. Extensive evaluations on long-horizon benchmarks using the Qwen-3 model family (4B to 32B) validate the effectiveness of TSUBASA, surpassing competitive memory-augmented systems that rely primarily on memory writing, such as Mem0 and Memory-R1. Our analyses further confirms that TSUBASA breaks the quality-efficiency barrier to achieve Pareto improvements, delivering robust, high-fidelity personalization with a reduced token budget.

Large language models are increasingly applied to multi-document and long-form inputs, yet long-context inference remains memory- and noise-inefficient. Key-value (KV) caching scales linearly with context length, while external retrieval methods often return lexically similar but causally irrelevant passages. We present S3-Attention, a memory-first inference-time framework that treats long-context processing as attention-aligned endogenous retrieval. S3-Attention decodes transient key and query projections into top-k sparse feature identifiers using lightweight sparse autoencoders, and constructs a CPU-based inverted index mapping features to token positions or spans during a single streaming scan. This design allows the KV cache to be discarded entirely and bounds GPU memory usage by the scan chunk size. At generation time, feature co-activation is used to retrieve compact evidence spans, optionally fused with BM25 for exact lexical matching. Under a unified LongBench evaluation protocol with fixed prompting, decoding, and matched token budgets, S3-Hybrid closely matches full-context inference across multiple model families and improves robustness in several information-dense settings. We also report an engineering limitation of the current prototype, which incurs higher wall-clock latency than optimized full-KV baselines, motivating future kernel-level optimization.

Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent hallucinations. To address these issues, we propose Self-Correcting RAG, a unified framework that reformulates retrieval and generation as constrained optimization and path planning. On the input side, we move beyond traditional greedy retrieval and, for the first time, formalize context selection as a multi-dimensional multiple-choice knapsack problem (MMKP), thereby maximizing information density and removing redundancy under a strict token budget. On the output side, we introduce a natural language inference (NLI)-guided Monte Carlo Tree Search (MCTS) mechanism, which leverages test-time compute to dynamically explore reasoning trajectories and validate the faithfulness of generated answers. Experiments on six multi-hop question answering and fact-checking datasets demonstrate that our method significantly improves reasoning accuracy on complex queries while effectively reducing hallucinations, outperforming strong existing baselines.Our code is available at https://github.com/xjiacs/Self-Correcting-RAG .

Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the token budget of modern language models, leading to severe context limitations and latency issues. We introduce Efficient Video Sampling (EVS), a simple, plug-and-play method for reducing token redundancy in videos by identifying and pruning temporally static patches -- spatial regions that remain unchanged across consecutive frames. EVS preserves positional identity, requires no architectural changes or retraining. We show that EVS substantially reduces token count while maintaining semantic fidelity, enabling faster inference and longer input sequences. Applied at inference time, EVS reduces large language model (LLM) time-to-first-token (TTFT) by up to 4x with minimal accuracy loss. When combined with an uptraining phase using stochastic pruning rates, EVS yields models that are robust to varying compression levels and retain full performance under aggressive pruning. Extensive experiments demonstrate that EVS consistently improves efficiency-accuracy trade-offs, unlocking scalable video-language understanding without sacrificing quality.

The deployment of Large Language Models (LLMs) faces a critical bottleneck when handling lengthy inputs: the prohibitive memory footprint of the Key Value (KV) cache. To address this bottleneck, the token pruning paradigm leverages attention sparsity to selectively retain a small, critical subset of tokens. However, existing approaches fall short, with static methods risking irreversible information loss and dynamic strategies employing heuristics that insufficiently capture the query-dependent nature of token importance. We propose FASA, a novel framework that achieves query-aware token eviction by dynamically predicting token importance. FASA stems from a novel insight into RoPE: the discovery of functional sparsity at the frequency-chunk (FC) level. Our key finding is that a small, identifiable subset of "dominant" FCs consistently exhibits high contextual agreement with the full attention head. This provides a robust and computationally free proxy for identifying salient tokens. %making them a powerful and efficient proxy for token importance. Building on this insight, FASA first identifies a critical set of tokens using dominant FCs, and then performs focused attention computation solely on this pruned subset. % Since accessing only a small fraction of the KV cache, FASA drastically lowers memory bandwidth requirements and computational cost. Across a spectrum of long-context tasks, from sequence modeling to complex CoT reasoning, FASA consistently outperforms all token-eviction baselines and achieves near-oracle accuracy, demonstrating remarkable robustness even under constraint budgets. Notably, on LongBench-V1, FASA reaches nearly 100\% of full-KV performance when only keeping 256 tokens, and achieves 2.56times speedup using just 18.9\% of the cache on AIME24.

Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and regulatory domains, particularly when dealing with numerous government documents. The top-k strategy frequently misses golden chunks, leading to incomplete or inaccurate answers. To address these retrieval bottlenecks, we explore two strategies to improve evidence coverage and answer quality. The first is a One-SHOT retrieval method that adaptively selects chunks based on a token budget, allowing as much relevant content as possible to be included within the model's context window. Additionally, we design modules to further filter and refine the chunks. The second is an iterative retrieval strategy built on a Reasoning Agentic RAG framework, where a reasoning LLM dynamically issues search queries, evaluates retrieved results, and progressively refines the context over multiple turns. We identify query drift and retrieval laziness issues and further design two modules to tackle them. Through extensive experiments on a dataset of government documents, we aim to offer practical insights and guidance for real-world applications in legal and regulatory domains.

Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive. Many common eviction policies use static recency windows or historical attention, leaving unused a signal computed on every decoding step: the model's current uncertainty. We introduce CONF-KV, a KV-cache manager that converts the next-token distribution into a scalar confidence score and uses it to choose the per-step cache budget, retaining more context when the model is uncertain and pruning aggressively when it is confident. Within each budget, tokens are ranked by a composite of accumulated attention mass and recency, while a protected recent window preserves local coherence. We combine the policy with blockwise online-softmax attention, mixed FP16/INT8 storage, and a pyramidal per-layer budget variant. Across four model families and generated lengths up to 4K, CONF-KV stays near the footprint of a fixed 512-token sliding window while remaining within 1.5--2.1 perplexity points of full KV. On Needle-in-a-Haystack up to 32K tokens, CONF-KV reaches 91.4% retrieval accuracy versus 53.8% for sliding windows and 80.6% for H2O; on 75 VisualWebArena tasks it retains 95.3% of full-KV success at 2.8 times lower peak memory.

While Large Language Models (LLMs) are increasingly deployed in long interactions, existing evaluations focus predominantly on retrospective memory (RM) via explicit queries. Prospective memory (PM), the critical ability to spontaneously recall and act on latent constraints without direct prompts, remains largely unevaluated. We introduce TriggerBench, a comprehensive PM benchmark spanning five dimensions across both daily assistants and professional workflows. TriggerBench pairs scenarios with matched RM controls, contrastive positive/negative variants, and overloaded triggers, enabling fine-grained measurement of proactive recall, false-alarm rate, and attentional robustness under a single protocol. Our evaluation yields three key findings. (i) PM shows a precision-recall trade-off and attentional fragility. Though enhanced reasoning significantly improves proactive recall, models may overfit to an "always-remind" heuristic. Furthermore, PM accuracy degrades substantially under implicit constraints or triggers overloaded by concurrent user requests, indicating that robust PM remains an open challenge. (ii) PM is notably harder than RM: on identical contexts, RM near-saturates up to 100K tokens, while PM decays sharply as context length scales. (iii) PM may serve as a behavioral probe of spare reasoning capacity. Pairing PM scenarios with AIME-2025 math problems reveals that successful trajectories yield higher PM accuracy than failed ones at the same context length, showing PM tracks spare reasoning budget that token count obscures. Project page: https://github.com/KristenZHANG/TriggerBench-Official.

A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques, such as in-context learning or re-prompting with state feedback, placing new importance on the token budget for the context window. An under-explored but natural next direction is to investigate LLMs as multi-robot task planners. However, long-horizon, heterogeneous multi-robot planning introduces new challenges of coordination while also pushing up against the limits of context window length. It is therefore critical to find token-efficient LLM planning frameworks that are also able to reason about the complexities of multi-robot coordination. In this work, we compare the task success rate and token efficiency of four multi-agent communication frameworks (centralized, decentralized, and two hybrid) as applied to four coordination-dependent multi-agent 2D task scenarios for increasing numbers of agents. We find that a hybrid framework achieves better task success rates across all four tasks and scales better to more agents. We further demonstrate the hybrid frameworks in 3D simulations where the vision-to-text problem and dynamical errors are considered. See our project website https://yongchao98.github.io/MIT-REALM-Multi-Robot/ for prompts, videos, and code.

Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits, compressing token budgets for both evidence collection and report writing, and preventing effective test-time scaling. We introduce FS-Researcher, a file-system-based, dual-agent framework that scales deep research beyond the context window via a persistent workspace. Specifically, a Context Builder agent acts as a librarian which browses the internet, writes structured notes, and archives raw sources into a hierarchical knowledge base that can grow far beyond context length. A Report Writer agent then composes the final report section by section, treating the knowledge base as the source of facts. In this framework, the file system serves as a durable external memory and a shared coordination medium across agents and sessions, enabling iterative refinement beyond the context window. Experiments on two open-ended benchmarks (DeepResearch Bench and DeepConsult) show that FS-Researcher achieves state-of-the-art report quality across different backbone models. Further analyses demonstrate a positive correlation between final report quality and the computation allocated to the Context Builder, validating effective test-time scaling under the file-system paradigm. The code and data are anonymously open-sourced at https://github.com/Ignoramus0817/FS-Researcher.

The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on stateless, eager schema injection imposes a hidden per-turn overhead the MCP Tax or Tools Tax that practitioner reports place between roughly 10k and 60k tokens in typical multi-server deployments. This payload inflates the key-value cache, is associated with reasoning degradation as context utilization approaches published fracture points around 70%, and turns token budgets into a recurring operational cost. We introduce Tool Attention, a middleware-layer mechanism that generalizes the "Attention Is All You Need" paradigm from self-attention over tokens to gated attention over tools. Tool Attention combines (i) an Intent Schema Overlap (ISO) score from sentence embeddings, (ii) a state-aware gating function enforcing preconditions and access scopes, and (iii) a two-phase lazy schema loader that keeps a compact summary pool in context and promotes full JSON schemas only for top-k gated tools. We evaluate on a simulated 120-tool, six-server benchmark whose per-server token counts are calibrated to public audits of real MCP deployments. In this simulation, Tool Attention directly reduces measured per-turn tool tokens by 95.0% (47.3k -> 2.4k) and raises effective context utilization (a token-ratio quantity) from 24% to 91%. End-to-end figures for task success, latency, cost, and reasoning quality are reported as projections derived from the measured token counts combined with published deployment telemetry; they are not measured on live LLM agents, and we mark projected values explicitly throughout. Taken together, the results support a simple thesis: protocol-level efficiency, not raw context length, is a binding constraint on scalable gentic systems. The code for this work is accessible at https://github.com/asadani/tool-attention

Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks, yet repository exploration remains a major bottleneck: locating relevant code consumes substantial token budget and pollutes the agent's context with irrelevant snippets. In most agents, the same model explores the repository and solves the task, leaving exploratory reads and searches in the solver's history. We present FastContext, a dedicated exploration subagent that separates repository exploration from solving. Invoked on demand, FastContext issues parallel tool calls and returns concise file paths and line ranges as focused context. FastContext is powered by specialized exploration models spanning 4B--30B parameters. We bootstrap them from strong reference-model trajectories and refine them with task-grounded rewards for broad first-turn search, multi-turn evidence gathering, and precise citation generation. Across SWE-bench Multilingual, SWE-bench Pro, and SWE-QA, integrating FastContext into Mini-SWE-Agent improves end-to-end resolution rates up to 5.5\% while reducing coding-agent token consumption up to 60\%, with marginal overhead. These results show that repository exploration can be separated from solving and handled effectively by specialized models. Code and data: https://github.com/microsoft/fastcontext

We propose SlowFast-LLaVA (or SF-LLaVA for short), a training-free video large language model (LLM) that can jointly capture the detailed spatial semantics and long-range temporal context without exceeding the token budget of commonly used LLMs. This is realized by using a two-stream SlowFast design of inputs for Video LLMs to aggregate features from sampled video frames in an effective way. Specifically, the Slow pathway extracts features at a low frame rate while keeping as many spatial details as possible (e.g., with 24x24 tokens), and the Fast pathway operates on a high frame rate but uses a larger spatial pooling stride (e.g., downsampling 6x) to focus on the motion cues. As a result, this design allows us to adequately capture both spatial and temporal features that are beneficial for understanding details along the video. Experimental results show that SF-LLaVA outperforms existing training-free methods on a wide range of video tasks. On some benchmarks, it achieves comparable or even better performance compared to state-of-the-art Video LLMs that are fine-tuned on video datasets.

Systems based on Large Language Models (LLMs) have become formidable tools for automating research and software production. However, their governance remains a challenge when technical requirements demand absolute consistency, auditability, and predictable control over cost and latency. Recent literature highlights two phenomena that aggravate this scenario: the stochastic variance inherent in the model's judgment (often treated as "systemic noise") and the substantial degradation of context utilization in long inputs, with critical losses when decisive information is diluted in the middle of the prompt. This article proposes PARCER as an engineering response to these limitations. The framework acts as a declarative "operational contract" in YAML, transforming unstructured interactions into versioned and executable artifacts. PARCER imposes strict governance structured into seven operational phases, introducing decision hygiene practices inspired by legal judgments to mitigate noise, adaptive token budgeting, formalized recovery routes (fallbacks) for context preservation, and systemic observability via OpenTelemetry. The objective of this work is to present the conceptual and technical architecture of PARCER, positioning it as a necessary transition from simple "prompt engineering" to "context engineering with governable governance".

As web agents (e.g., Deep Research) routinely consume massive volumes of web pages to gather and analyze information, LLM context management -- under large token budgets and low signal density -- emerges as a foundational, high-importance, and technically challenging problem for agentic and RAG pipelines. Existing solutions for extracting relevant content are inadequate: generative extraction models suffer from high latency, rule-based heuristics lack adaptability, and chunk-and-rerank methods are blind to webpage structure. To overcome these issues, we introduce Index-based Web Content Extraction to reframe the extraction process from slow, token-by-token generation into a highly efficient, discriminative task of index prediction, achieving both effectiveness and efficiency. We partition HTML into structure-aware, addressable segments, and extract only the positional indices of content relevant to a given query. This method decouples extraction latency from content length, enabling rapid, query-relevant extraction. We first evaluate our method as a post-retrieval processing component within an RAG QA system and find that it improves QA accuracy. Then we directly measure its match rate with the target content in two scenarios: main content extraction (ME) and query-relevant extraction (QE). Experimental results show that our method outperforms existing works in both accuracy and speed, effectively bridging the gap between LLMs and the vast webpages.

Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training or on heuristic token eviction, creating an undesirable trade-off among efficiency, training cost, and accuracy. In this work, we show that full-attention LLMs are already intrinsically sparse and can be transformed into highly sparse models with only minimal adaptation. Our approach is built on three observations: (1) only a small subset of attention heads truly requires full long-context processing; (2) long-range retrieval is governed primarily by a low-dimensional subspace, allowing relevant tokens to be retrieved efficiently with a 16-dimensional indexer; and (3) the useful token budget is strongly query-dependent, making dynamic top-p selection more suitable than fixed top-k sparsification. Based on these insights, we propose RTPurbo, which retains the full KV cache only for retrieval heads and introduces a lightweight token indexer for sparse attention. By exploiting the model's intrinsic sparsity, RTPurbo achieves sparsification with only a few hundred training steps. Experiments on long-context benchmarks and reasoning tasks show that RTPurbo preserves near-lossless accuracy while delivering substantial efficiency gains, including up to a 9.36times prefill speedup at 1M context and about a 2.01times decode speedup. These results suggest that strong sparse inference can be obtained from standard full-attention training without expensive native sparse pretraining.

Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation, yet single-agent systems exhibit fundamental limitations when confronted with complex research tasks demanding multi-source synthesis, adversarial verification, and personalized delivery. We present DOVA (Deep Orchestrated Versatile Agent), a multi-agent platform introducing three key innovations: (1) deliberation-first orchestration, where explicit meta-reasoning precedes tool invocation, informed by a persistent user model and entity-aware conversation context; (2) hybrid collaborative reasoning, a composable three-phase pipeline unifying ensemble diversity, blackboard transparency, and iterative refinement; and (3) adaptive multi-tiered thinking, a six-level token-budget allocation scheme that reduces inference cost by 40-60% on simple tasks while preserving deep reasoning capacity. We formalize the core algorithms, present an architectural ablation study across seven system configurations, and analyze the contribution of each component to answer confidence, source coverage, and token efficiency.

Existing Multimodal Large Language Models (MLLMs) remain primarily reactive, failing to continuously perceive environments or proactively assist users. While emerging benchmarks address proactivity, they are largely confined to alert scenarios, neglect personalized context, and fail to evaluate the precise timing of human-machine interactions (HMI).In this paper, we introduce EgoPro-Bench, a novel benchmark for training and evaluating proactive interaction capabilities based on streaming egocentric videos; it comprises 2,400 videos in the evaluation set and over 12,000 videos in the training set.Unlike previous works, EgoPro-Bench leverages simulated user profiles to generate diverse user intentions and to construct high-fidelity HMI data across 12 distinct domains.Subsequently, we propose a specialized evaluation protocol and metrics, train proactive interaction models designed for efficient reasoning and low-latency interaction on streaming video data, and conduct comprehensive evaluations.Furthermore, we introduce an interaction principle termed "short thinking, better interaction", which allocates a limited token budget prior to intent recognition, thereby enhancing interaction performance.The experiments demonstrate that EgoPro-Bench substantially enhances the intention understanding capabilities of MLLMs and enables accurate identification of appropriate timings for HMI, thereby laying a solid foundation for next-generation user-centric proactive interactive agents.

Commercial large language models bill, scale latency, and budget context per token. Yet tokenizers assign more subword tokens to the same meaning in some languages than in others, so speakers of languages with high token-fertility pay a structural penalty before a model is ever invoked. This penalty is documented for multilingual settings in general, but it has not been measured systematically for African languages at the level of enterprise deployment economics and cognitive context capacity. We measure it across 20 African languages spanning five language families and three scripts (Latin, Ge'ez/Ethiopic, N'Ko; 19 appear in the primary FLORES-200+ corpus, with Nigerian Pidgin measured via MAFAND-MT only), using parallel corpora so that the language effect is isolated from content. Across 11 frontier and open tokenizers on FLORES-200+, every African language carries a tokenization premium above English (median 1.88x on GPT-5 / o200k_base, up to 8.92x for N'Ko); the penalty is largest for Ethiopic and N'Ko scripts (reaching 7-9x) and is near-invariant across corpora (FLORES vs SIB-200 Pearson r = 0.9998). Translated into deployment terms, this results in up to 8.9x inference cost and an equivalent generation-latency multiplier (N'Ko vs English on GPT-5; 7.4x for Amharic), and as little as 11% of English's effective context window. The best currently available tokenizer for African languages, Gemma 4, reduces the mean premium from 3.31x (cl100k_base) to 2.38x, but no tokenizer eliminates the penalty. We release an open measurement tool (afri-fertility), a public leaderboard, a results dataset, and mitigation guidance for African builders. The penalty falls hardest on the languages whose speakers can least afford it, a digital divide encoded directly into the subword vocabulary.

Vision-language models (VLMs) are increasingly augmented with continuous or latent non-textual tokens intended to support "visual thinking." Despite improved task accuracy, this alone does not show that models actually use these tokens for reasoning -- gains may arise from confounds such as added context length, special-token anchoring, or training-time regularization. We formalize a diagnostic principle, Ablate-to-Validate, for testing whether latent-token content is genuinely utilized, and instantiate it as the Token Replacement Test (TRT), a standardized suite of content-replacement ablations. TRT holds the prompt, image, token budget, and decoding fixed while replacing intermediate tokens with zero, random, first-repeat, or oracle alternatives, isolating whether performance depends on token content or merely on token presence. As a controlled testbed, we study relative depth reasoning with LLaVA-13B and Qwen2.5-VL-3B, training models to predict and consume continuous or discrete depth spans across multiple frozen encoders (SigLIP2, CLIP, DINOv2) and token budgets. We additionally apply TRT to three off-the-shelf visual-thinking systems (Mirage, Mull-Tokens, CoVT) on BLINK, VSP, and CV-Bench. Across all settings, accuracy gains are a misleading proxy for latent-token reasoning: VLMs retain most improvement even when token content is corrupted or replaced, revealing a persistent gap between having a latent channel and using it as an information bottleneck. We recommend TRT as a standard diagnostic alongside accuracy for any method introducing continuous thought tokens.

Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the repository files needed for the task. We introduce Agent Retrieval Bench, a file-level benchmark for this upstream retrieval problem. Samples are built from real coding-workflow signals and evaluated against frozen base-commit repositories, with relevance defined by what an agent needs next rather than direct query-file semantic similarity. The benchmark covers four positive-retrieval tasks: code2test, comment2context, trace2code, and edit2ripple; a fifth subset evaluates selective retrieval using natural evidence-backed no-gold cases and counterfactual wrong-repository controls. Agent Retrieval Bench contains 427 samples across 25 repositories: 345 positive examples, 50 natural no-gold examples, and 32 counterfactual controls. The corpus includes 308 base-commit snapshots, 392,000 files, and 7.9 million chunks. We evaluate lexical retrieval, RepoMap, open-source embeddings, selective abstention, and logged agent context selection. No single retrieval family dominates: Qwen3-Embedding-4B has the best sample-weighted MRR on positive samples, Qwen3-Embedding-8B the best Recall@20, and RepoMap the best budgeted context yield at 8K tokens, with task-level winners differing substantially. Selective thresholds calibrated with counterfactual controls do not improve selective success on natural no-gold cases, revealing a calibration gap. Logged trajectories also miss every gold file on 27-35 percent of samples. A controlled seed-intervention pilot finds that retrieval-derived initial context yields higher file F1 with less post-seed exploration than random non-gold context, while oracle gold context shows substantial remaining headroom.

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightMem2 at https://github.com/zjunlp/LightMem2.

We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and producing reports. The private eval set comprises 160 tasks, split across 10 worlds. Each world contains an accounting system, as well as spreadsheets, PDFs, and other files. Every task was authored and solved by experts in accounting and bookkeeping, who also wrote grading rubrics. Across nine frontier models, Claude-Fable-5 (Max) leads with 56.4% Mean Criteria@3, ahead of Muse-Spark-1.1 (xHigh) at 52.6%. No model scores more than 2.6% Pass^8 (GPT-5.6-Sol (Max+Pro)) and the highest Pass@8 is 21.5% (Muse-Spark-1.1 (xHigh)). We experiment with increasing the token budget from 1 to 50 and observe an instance of Simpson's paradox: scores increase as the token budget increases but within a given budget-constrained harness, scores are lower on tasks where the model spends more tokens. As APEX-Accounting is a closed benchmark, leaderboard evals can be run for any frontier model on request.

Context-reduction layers for API-based coding agents, including command-output compressors, retrieval rankers, and API-boundary proxies, are commonly evaluated by how much context or tool output they remove. We ask a different question: which interventions actually reduce end-to-end billed cost while preserving task success? Our primary evidence is a pre-specified, hash-frozen, paired campaign of 2,908 provider-billed Claude Code runs, of which 2,848 were analyzed, covering 103 tasks, seven repositories, and three models. The campaign compared a baseline with two generations of hook-based compression and an API-boundary proxy within a broader measured program of roughly 5,500 billed executions. Three findings emerge. First, prompt-cache traffic dominated cost composition, accounting for about 87% of reconstructed four-component cost (about 80% of the actual bill), with an 8.7% dollar-weighted residual not attributable from retained telemetry. Second, local payload reduction was not a reliable predictor of end-to-end billed cost. An arm that removed 38% of estimated raw tool-output tokens incurred 6.8% higher paired cost (95% CI: +2.8% to +11.3%), while per-task reduction showed only a weak association with cost change (Pearson r = 0.15). Third, aggressive compression can remove action-critical evidence: on SWE-bench-derived Go tasks, compression reduced successful patch application from 27/40 to 15/40 by corrupting verbatim edit anchors. We propose evaluating context-reduction systems by success-adjusted billed cost rather than token reduction alone.

Recent advancements in Large Language Models (LLMs) have leveraged increased test-time computation to enhance reasoning capabilities, a strategy that, while effective, incurs significant latency and resource costs, limiting their applicability in real-world time-constrained or cost-sensitive scenarios. This paper introduces BudgetThinker, a novel framework designed to empower LLMs with budget-aware reasoning, enabling precise control over the length of their thought processes. We propose a methodology that periodically inserts special control tokens during inference to continuously inform the model of its remaining token budget. This approach is coupled with a comprehensive two-stage training pipeline, beginning with Supervised Fine-Tuning (SFT) to familiarize the model with budget constraints, followed by a curriculum-based Reinforcement Learning (RL) phase that utilizes a length-aware reward function to optimize for both accuracy and budget adherence. We demonstrate that BudgetThinker significantly surpasses strong baselines in maintaining performance across a variety of reasoning budgets on challenging mathematical benchmarks. Our method provides a scalable and effective solution for developing efficient and controllable LLM reasoning, making advanced models more practical for deployment in resource-constrained and real-time environments.

Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as it incurs excessive inference costs with disproportionate performance gains. Controlling reasoning length without sacrificing performance is therefore important, but remains challenging, especially under tight thinking budgets. We propose budget guidance, a simple yet effective method for steering the reasoning process of LLMs toward a target budget without requiring any LLM fine-tuning. Our approach introduces a lightweight predictor that models a Gamma distribution over the remaining thinking length during next-token generation. This signal is then used to guide generation in a soft, token-level manner, ensuring that the overall reasoning trace adheres to the specified thinking budget. Budget guidance enables natural control of the thinking length, along with significant token efficiency improvements over baseline methods on challenging math benchmarks. For instance, it achieves up to a 26% accuracy gain on the MATH-500 benchmark under tight budgets compared to baseline methods, while maintaining competitive accuracy with only 63% of the thinking tokens used by the full-thinking model. Budget guidance also generalizes to broader task domains and exhibits emergent capabilities, such as estimating question difficulty. The source code is available at: https://github.com/UMass-Embodied-AGI/BudgetGuidance.

Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but their long audio-video token sequences introduce substantial memory and inference costs. Existing compression methods mainly focus on selecting important tokens under fixed budgets, leaving the preceding budget-allocation problem underexplored. We show that direct query-to-audio/video similarity is unreliable for inter-modal budget allocation, and that uniform intra-modal budgets can miss key evidence while retaining redundant content. To address these limitations, we propose OmniDelta, a training-free, skill-driven framework that couples intent-aware inter-modal allocation with content-aware intra-modal allocation. OmniDelta first constructs audio and video skill pools to shift the fixed retained-token budget according to query demand, then reallocates modality budgets over audio segments and video frames using local complexity and temporal redundancy. The resulting local budgets can be combined with existing pruning strategies, preserving the total retained-token ratio while changing where the budget is spent. Experiments on four audio-video benchmarks with two Qwen2.5-Omni models show that OmniDelta establishes a new accuracy-efficiency Pareto frontier across pruning ratios. At 25% token retention on Qwen2.5-Omni-7B, OmniDelta reduces GPU memory by 22.0% and achieves a 1.64x end-to-end speedup over full-token inference.

Reasoning is critical for large language models (LLMs) to excel in a wide range of tasks. While methods like Chain-of-Thought (CoT) reasoning enhance LLM performance by decomposing problems into intermediate steps, they also incur significant overhead in token usage, leading to increased costs. We find that the reasoning process of current LLMs is unnecessarily lengthy and it can be compressed by including a reasonable token budget in the prompt, but the choice of token budget plays a crucial role in the actual compression effectiveness. We then propose a token-budget-aware LLM reasoning framework, which dynamically estimates token budgets for different problems based on reasoning complexity and uses the estimated token budgets to guide the reasoning process. Experiments show that our method effectively reduces token costs in CoT reasoning with only a slight performance reduction, offering a practical solution to balance efficiency and accuracy in LLM reasoning. Code: https://github.com/GeniusHTX/TALE.

Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations. The incumbent response treats this as a storage-and-retrieval problem. We argue that framing is too narrow. Actively managing what an agent holds in mind is a lifecycle, not merely a store: it spans deciding what to remember, extracting and structuring it, choosing the right store per data type, consolidating and forgetting while preserving provenance, deciding what is relevant now, anticipating what is needed next, and compacting context to a budget without losing what matters. In serious production this operates not over a single user but across an organizational scope hierarchy. We name this discipline Agentic Context Management (ACM) and decompose it into five primitives: architecting, ingesting, scoping, anticipating, and compacting & consolidation. We then make the economic case: naive context accumulation grows token cost quadratically in conversation length, crude summarization buys linear cost at the price of an accuracy cliff, and only validated compaction achieves linear cost with preserved fidelity. We describe a reference implementation, Maximem Synap, that realizes the five primitives as a multi-tenant service and reports 92% on LongMemEval and 93.2% on LoCoMo under the configuration detailed in Section 6. We close with dimensions existing benchmarks do not yet capture, latency, token efficiency, and context-rot resistance, and the frontier of decision-level and organization-level context the category points toward.

Large language models can now process increasingly long inputs, yet their ability to effectively use information spread across long contexts remains limited. We trace this gap to how attention budget is spent during supervised fine-tuning (SFT) on long sequences: positional biases and attention sinks cause the model to allocate most of its attention to positionally privileged tokens rather than semantically relevant content. This training-time attention dilution (the starvation of content tokens in the attention distribution) weakens the gradient signal, limiting the model's ability to learn robust long-context capabilities. We introduce FocuSFT, a bilevel optimization framework that addresses this problem at training time. An inner loop adapts lightweight fast-weight parameters on the training context to form a parametric memory that concentrates attention on relevant content, and the outer loop performs SFT conditioned on this sharpened representation. Both loops apply bidirectional attention over context tokens while preserving causal masking for responses, reducing the causal asymmetry that gives rise to attention sinks and aligning inner-outer behavior. On BABILong, FocuSFT improves accuracy by up to +14pp across 4K--32K context lengths; on RULER, it raises CWE aggregation from 72.9\% to 81.1\% at 16K; and on GPQA with agentic tool use, it yields a 24\% relative gain in pass@1. Attention analysis shows that FocuSFT reduces attention sink mass by 529times and triples context engagement during training. Code: https://github.com/JarvisPei/FocuSFT

High-resolution Vision-Language Models (VLMs) have been widely used in multimodal tasks to enhance accuracy by preserving detailed image information. However, these models often generate excessive visual tokens due to encoding multiple partitions of the input image. Processing these excessive visual tokens is computationally challenging, especially in resource-constrained environments with commodity GPUs. To support high-resolution images while meeting resource constraints, we propose High-Resolution Early Dropping (HiRED), a token-dropping scheme that operates within a fixed token budget before the Large Language Model (LLM) stage. HiRED can be integrated with existing high-resolution VLMs in a plug-and-play manner, as it requires no additional training while still maintaining superior accuracy. We strategically use the vision encoder's attention in the initial layers to assess the visual content of each image partition and allocate the token budget accordingly. Then, using the attention in the final layer, we select the most important visual tokens from each partition within the allocated budget, dropping the rest. Empirically, when applied to LLaVA-Next-7B on NVIDIA TESLA P40 GPU, HiRED with a 20% token budget increases token generation throughput by 4.7, reduces first-token generation latency by 15 seconds, and saves 2.3 GB of GPU memory for a single inference.

Transformers and deep state space models (SSMs) sit at opposite ends of a basic design choice: attention routes each query through a growing key-value (KV) cache by content-based matching at quadratic cost, while deep SSMs compress context into a fixed-size recurrent state that is not directly addressed by query-key matching. We propose Interdomain Attention, which integrates an SSM into an attention module through kernel methods: an attention kernel is approximated by a finite feature map, the resulting key features and values are projected onto a shared set of basis functions maintained by a single SSM recurrence, and each query attends to the compressed coefficients through its own feature map, recovering query-conditioned attention over a fixed-size state. The scalable layer is a learned relaxation of this derivation, and we validate its components through ablations. In a 125M to 1.3B autoregressive language-modeling study on FineWeb-Edu at matched recurrent-state budget, Interdomain Attention improves on an SSM token mixer at every scale, surpasses a same-recipe softmax baseline at 1.3B on validation perplexity and on the eight-task commonsense suite, and inherits the length-flat behavior of its fixed-state core out to 3.5x the training context. Ablations indicate that the query-conditioned projection is the main source of the gain.

Clinical machine learning increasingly relies on training corpora generated by large language models (LLMs) rather than annotated by clinicians, and such corpora are described and reused largely on the basis of their reported scale. We test whether volume reflects information content. Analysing the complete output of a multi-agent clinical extraction pipeline applied to 167,034 patient narratives, 2.51 billion generated tokens across the ten text-bearing channels of an eleven-channel pipeline, we introduce Provenance-based Redundancy Decomposition, a token-level classification of the entire output by source. Only 10.9% of the output is trainable-unique content while 79.4% is redundant; raw token count overstates information content by roughly ninefold. The redundancy arises through two distinct mechanisms, verbatim copying of source context into per-item fields, and duplication of generated text across records, of which only the former is losslessly removable. An independent, model-free analysis based on lossless compression confirms the redundancy, recovering the two mechanisms without reference to the provenance labels. One pipeline channel carries almost no redundancy, showing that the level of redundancy depends on how each channel is structured rather than being a fixed property of LLM extraction. Because uncorrected redundancy up-weights the longer, more complex presentations that generate the most items, it skews the token-level training distribution of the corpus, a property we measure directly. In a controlled downstream test, de-duplicating the corpus before adaptation improved a clinical encoder on external disease-recognition benchmarks at equal token budget, robustly across adaptation depths and replicated on a second benchmark, confirming that the redundancy carries a measurable cost beyond storage. The classification tool is released openly.

Large language models (LLMs) owe much of their stellar performance to expansive input contexts, yet such verbosity inflates monetary costs, carbon footprint, and inference-time latency. Much of this overhead manifests from the redundant low-utility tokens present in typical prompts, as only a fraction of tokens typically carries the majority of the semantic weight. We address this inefficiency by introducing FrugalPrompt, a novel prompt compression framework for LLMs, which retains only the most semantically significant tokens. Leveraging two state-of-the-art token attribution methods, GlobEnc and DecompX, we assign salience scores to every token in an input sequence, rank them to preserve the top-k% tokens in their original order, and obtain a sparse frugalized prompt. We evaluate the approach across four NLP tasks: Sentiment Analysis, Commonsense QA, Summarization, and Mathematical Reasoning, using a suite of frontier LLMs. For the first three tasks, a 20% prompt reduction incurs only a marginal loss in task performance, demonstrating that contemporary LLMs can reconstruct elided context from high-salience cues. In contrast, performance on mathematical reasoning deteriorates sharply, reflecting a stronger dependence on complete token continuity. Further analysis with bottom-k% and random-k% tokens reveals asymmetric performance patterns that may suggest potential task contamination effects, wherein models may resort to shallow memorized patterns from pretraining exposure for conventional NLP tasks. We posit that our work contributes to a more nuanced understanding of LLM behavior in performance-efficiency trade-offs, and delineate the boundary between tasks tolerant to contextual sparsity and those requiring exhaustive context. Our source code and models are available at: https://github.com/Starscream-11813/Frugal-ICL.

We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of multimodal benchmarks. The model builds on a native OneVision-Encoder and incorporates Windowed Attention for efficient local computation while maintaining native resolution. Its key advance is codec-stream tokenization: it treats compressed video as a continuous bit-cost stream, where bit-cost dynamics determine adaptive temporal groups, and motion-residual cues select salient spatial evidence into compact visual canvases. This allocation concentrates a limited token budget on event-bearing content, enabling more stable long-video token compression than fixed groups of pictures. A shared 3D RoPE further places codec canvases, sampled frames, and images in a unified spatiotemporal coordinate system. Furthermore, we build the LLaVA-OV-2 data and training stack around large-scale open supervision: approximately 8M re-captioned video samples for pretraining, a 4M-sample spatial corpus for fine-tuning. We also introduce JumpScore, a temporal-localization benchmark targeting fine-grained grounding in high-frequency, densely repeated motion, a regime underrepresented by existing video evaluations. A standout capability of LLaVA-OV-2 is its unified perception across video understanding, temporal grounding, spatial grounding, and manipulation-trace reasoning. On JumpScore, LLaVA-OneVision-2-8B reaches 74.9 JumpScore mAP, surpassing Qwen3-VL-8B (30.1) by +44.8 points; under matched visual-token budgets on the same benchmark, codec-stream inputs improve temporal grounding over frame sampling by +9.7 points. Across standard benchmarks, LLaVA-OneVision-2-8B further outperforms Qwen3-VL-8B by +4.3 average points on video tasks, +5.3 on spatial tasks, and +15.6 average J&F on tracking tasks.

Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget. We identify a structural failure in this procedure: independent selection can split dependent evidence pairs, retaining one member while deleting the other. When retained text contains an answer but deleted text defines the entity needed to interpret it, we call the result referential dangling. At a compression ratio of 0.30, Beaver, which ranks coherent chunks using Qwen3-0.6B embeddings, leaves the answer path incomplete in 34-54% of bridge examples across three multi-hop question answering datasets. On a shared HotpotQA bridge set, all six hard compressors we test exhibit dangling at rates up to 60%, and every document in LongBench-v2 Single-Document QA contains at least one dangling reference. On dangling examples evaluated with Qwen3-8B, reinserting the missing supporting paragraph while removing nonsupporting paragraphs to maintain the token budget improves accuracy by 29-34 percentage points (p < 0.0001), recovering at least 88% of the gap to contexts retaining both supporting paragraphs. Stronger answer models do not absorb the loss: on MuSiQue, GPT-5.5 is 8.8 points less accurate on compressed contexts than on contexts retaining both supporting paragraphs. Finally, we train a compact classifier to rank omitted sentences by whether they are needed to interpret retained text and reinsert the top-ranked candidates without support annotations at inference. On HotpotQA with Qwen3-8B, this automatic restoration improves accuracy by 4.7 points while changing the compression ratio only from 0.30 to 0.31. Hard compressors should optimize both relevance and referential completeness.

Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in training and linearly scaling memory costs during inference. Recent State Space Models (SSMs) such as Mamba offer alternatives with constant memory usage, but they underperform in tasks requiring extensive in-context retrieval. We introduce Taipan, a novel hybrid architecture that combines Mamba-2 with Selective Attention Layers (SALs). These SALs identify tokens requiring long-range interactions, remove less important features, and then augment their representations using the attention module. This approach balances Mamba's efficiency with Transformer-like performance in memory-intensive tasks. By constraining the attention budget, Taipan extends accurate predictions to context lengths of up to 1 million tokens while preserving computational efficiency. Our experiments demonstrate Taipan's superior performance across various scales and tasks, offering a promising solution for efficient long-context language modeling.

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source state is already computed during ordinary decoding, LRT adds a cross-layer recurrent latent pathway across positions without inserting pause tokens or extra depth loops, and the standard attention mechanism and KV-cache interface are preserved. To pretrain this recurrence at scale without sequentially unrolling the transformer, we introduce interleaved parallel training: a single full-sequence initialization forward pass builds a shared buffer; then disjoint position subsets are refined in parallel and written back, so that all tokens receive recurrent-memory-aware supervision at roughly 2 times baseline compute. Across nanochat style backbones and a wide range of tokens-per-parameter budgets, LRT improves both language-modeling loss and in-context learning under matched effective compute while adding as little as 0.3% parameters.

Large pre-trained neural language models have brought immense progress to both NLP and software engineering. Models in OpenAI's GPT series now dwarf Google's BERT and Meta's RoBERTa, which previously set new benchmarks on a wide range of NLP applications. These models are trained on massive corpora of heterogeneous data from web crawls, which enables them to learn general language patterns and semantic relationships. However, the largest models are both expensive to train and deploy and are often closed-source, so we lack access to their data and design decisions. We argue that this trend towards large, general-purpose models should be complemented with single-purpose, more modestly sized pre-trained models. In this work, we take StackOverflow (SO) as a domain example in which large volumes of rich aligned code and text data is available. We adopt standard practices for pre-training large language models, including using a very large context size (2,048 tokens), batch size (0.5M tokens) and training set (27B tokens), coupled with a powerful toolkit (Megatron-LM), to train two models: SOBertBase, with 109M parameters, and SOBertLarge with 762M parameters, at a budget of just 187 and \800 each. We compare the performance of our models with both the previous SOTA model trained on SO data exclusively as well general-purpose BERT models and OpenAI's ChatGPT on four SO-specific downstream tasks - question quality prediction, closed question prediction, named entity recognition and obsoletion prediction (a new task we introduce). Not only do our models consistently outperform all baselines, the smaller model is often sufficient for strong results. Both models are released to the public. These results demonstrate that pre-training both extensively and properly on in-domain data can yield a powerful and affordable alternative to leveraging closed-source general-purpose models.

Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hinges on a few local decisions. Existing online policy distillation (OPD) provides denser token-level supervision, but typically treats heterogeneous agent trajectories as monolithic strings rather than causal interaction units. We present StepOPSD, a post-rollout preference self-distillation framework that takes the agent step as the unit of credit redistribution. StepOPSD decomposes trajectories into action-centered step segments, rescoring them under hindsight-enriched teacher contexts and converting token-level log-probability gaps into sign-preserving advantage shaping with a normalized per-step credit budget before the GRPO update. Across ALFWorld and Search-QA with Qwen3-1.7B and Qwen2.5-3B-Instruct, StepOPSD attains best or second-best results on subsets most sensitive to local causal errors, including first-place performance on ALFWorld Heat (79.1%), PickTwo (95.0%), Search-QA TriviaQA (61.6%), and tied-best performance on HotpotQA (40.4%). The results further reveal a consistent two-knob law: smaller α_clip acts as a broadly stabilizing local trust region, whereas the optimal global mixing strength λ_mix remains task-dependent. These findings suggest that step-aware distillation is most useful when trajectory-level rewards are weakly aligned with the local action that determines downstream success.

Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and reasoning, leading to long, disorganized contexts where small perceptual mistakes may cascade into completely wrong answers. Moreover, expensive reinforcement learning with hand-crafted rewards is required to achieve good performance. Here, we introduce SPARC (Separating Perception And Reasoning Circuits), a modular framework that explicitly decouples visual perception from reasoning. Inspired by sequential sensory-to-cognitive processing in the brain, SPARC implements a two-stage pipeline where the model first performs explicit visual search to localize question-relevant regions, then conditions its reasoning on those regions to produce the final answer. This separation enables independent test-time scaling with asymmetric compute allocation (e.g., prioritizing perceptual processing under distribution shift), supports selective optimization (e.g., improving the perceptual stage alone when it is the bottleneck for end-to-end performance), and accommodates compressed contexts by running global search at lower image resolutions and allocating high-resolution processing only to selected regions, thereby reducing total visual tokens count and compute. Across challenging visual reasoning benchmarks, SPARC outperforms monolithic baselines and strong visual-grounding approaches. For instance, SPARC improves the accuracy of Qwen3VL-4B on the V^* VQA benchmark by 6.7 percentage points, and it surpasses "thinking with images" by 4.6 points on a challenging OOD task despite requiring a 200times lower token budget.

Encoder-only Transformers have advanced along three axes -- architecture, data, and systems -- yielding Pareto gains in accuracy, speed, and memory efficiency. Yet these improvements have not fully transferred to Chinese, where tokenization and morphology differ markedly from English. We introduce Chinese ModernBERT, a from-scratch Chinese encoder that couples: (i) a hardware-aware 32k BPE vocabulary tailored to frequent Chinese affixes/compounds, lowering the embedding budget; (ii) whole-word masking (WWM) with a dynamic masking curriculum (30% -> 15%) to align task difficulty with training progress; (iii) a two-stage pre-training pipeline that extends the native context from 1,024 to 8,192 tokens using RoPE and alternating local/global attention; and (iv) a damped-cosine learning-rate schedule for stable long-horizon optimization. We pre-train on ~1.2T Chinese tokens from CCI3-HQ, CCI4 (Chinese), and Cosmopedia-Chinese. On CLUE, Chinese ModernBERT is competitive with strong Chinese encoders under a unified fine-tuning protocol. Under bf16 it achieves high long-sequence throughput while maintaining strong short-sequence speed, reflecting benefits from budget allocation and attention design. To probe retrieval-oriented quality, we add a small amount of open contrastive data: fine-tuning on SimCLUE (~3M pairs) improves further when adding T2Ranking (~2M), reaching 0.505 (Pearson) / 0.537 (Spearman) on the SimCLUE test set. Under this open-data setting, Chinese ModernBERT surpasses Qwen-0.6B-embedding on SimCLUE, suggesting a clear scaling path for STS with additional curated pairs. We will release tokenizer and weights to facilitate reproducible research.

Frontier LLMs are increasingly utilised across academia, society and industry. A commonly used unit for comparing models, their inputs and outputs, and estimating inference pricing is the token. In general, tokens are used as a stable currency, assumed to be broadly consistent across tokenizers and contexts, enabling direct comparisons. However, tokenization varies significantly across models and domains of text, making naive interpretation of token counts problematic. We quantify this variation by providing a comprehensive empirical analysis of tokenization, exploring the compression of sequences to tokens across different distributions of textual data. Our analysis challenges commonly held heuristics about token lengths, finding them to be overly simplistic. We hope the insights of our study add clarity and intuition toward tokenization in contemporary LLMs.

Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value. Falling per-token prices mask the pattern; total spend rises anyway. We argue the decisive lever against token maxing is the harness: the orchestration layer that assembles context, exposes tools, sequences turns, delegates work, and carries enterprise observability and governance. We isolate it with a controlled swap: 22 locked evaluation tasks, six foundation models (Claude Sonnet 4.6, Gemini 3.1, Gemini Flash 3.5, Qwen 3.6, GLM 5.1, Palmyra X6), changing only the orchestration layer -- a frozen conventional production loop versus the Writer Agent Harness. Holding models constant, the harness cuts blended cost per task 41% (0.21->0.12), median wall-clock 44% (48s->27s), and tokens per task 38% (14.2k->8.8k), with task-completion quality at parity (0.78->0.81, directional at this sample size). Efficiency is model-invariant -- every model gets cheaper (33-61%) -- while quality gains are capability-dependent: a model's gain correlates almost perfectly with its baseline strength (r=0.99, n=6), a phenomenon we term harness leverage. Quality per dollar rises 82%; task-completions per million tokens rise from 54.9 to 92.0. On this workload the orchestration layer moved cost per task more than the full spread of the model menu did. We formalize token economics at the orchestration layer (including effective input price under prompt caching), detail the six mechanism families behind the effect -- cache-shape discipline to failure-spend governance -- compare six widely used agent systems on the same axes, and argue the harness is the one component whose efficiency multiplies across every model an organization runs -- present and future.

Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text. A benchmark over these four signals is hard to build because finance violates four assumptions of time-series evaluation: text must be gated by its publication date to prevent look-ahead, quarterly fundamentals are reported with a one- to ninety-day lag, filing text is partly redundant with the numerical statement fields it accompanies, and macroeconomic regimes leak across calendar splits. No public benchmark addresses all four signals jointly. MacroLens covers 4,416 U.S. small- and micro-cap equities over 2021-2026. Seven tasks share one point-in-time panel of prices, 46.8M XBRL accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles, plus a scenario layer of 1,130 macroeconomic events across 49 types automatically detected and rendered as natural language. Tasks span contextual forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation. We evaluate 19 methods across six families spanning naive heuristics through time-series foundation models, fine-tuned LLM-based time-series models, and zero-shot large language models (LLMs), plus a five-step feature-context ablation on two frontier LLMs and a gradient-boosted baseline. MacroLens is released at https://huggingface.co/datasets/DeepAuto-AI/MacroLens.

LLM-based agents show strong potential for long-horizon reasoning, yet their context size is limited by deployment factors (e.g., memory, latency, and cost), yielding a constrained context budget. As interaction histories grow, this induces a trade-off between retaining past information and staying within the context limit. To address this challenge, we propose Budget-Aware Context Management (BACM), which formulates context management as a sequential decision problem with a context budget constraint. It enables agents to assess the available budget before incorporating new observations and decide when and how much of the interaction history to compress. We further develop BACM-RL, an end-to-end curriculum-based reinforcement learning approach that learns compression strategies under varying context budgets. Experiments on compositional multi-objective QA and long-horizon web browsing benchmarks show that BACM-RL consistently outperforms prior methods across model scales and task complexities, achieving over 1.6times gains over strong baselines in high-complexity settings, while maintaining strong advantages as budgets shrink, where most methods exhibit a downward performance trend.

Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. Despite recent strides in making LLMs process contexts with more than 100K tokens, there is currently a lack of a standardized benchmark to evaluate this long-context capability. Existing public benchmarks typically focus on contexts around 10K tokens, limiting the assessment and comparison of LLMs in processing longer contexts. In this paper, we propose inftyBench, the first LLM benchmark featuring an average data length surpassing 100K tokens. inftyBench comprises synthetic and realistic tasks spanning diverse domains, presented in both English and Chinese. The tasks in inftyBench are designed to require well understanding of long dependencies in contexts, and make simply retrieving a limited number of passages from contexts not sufficient for these tasks. In our experiments, based on inftyBench, we evaluate the state-of-the-art proprietary and open-source LLMs tailored for processing long contexts. The results indicate that existing long context LLMs still require significant advancements to effectively process 100K+ context. We further present three intriguing analyses regarding the behavior of LLMs processing long context.

Reinforcement learning with verifiable rewards (RLVR) generates hundreds of thousands of tokens per training step, with rollout generation dominating the computational cost. The overall token budget can be controlled along two main dimensions: (i) deciding which prompts to allocate rollouts to, and (ii) deciding how long each rollout should be. Prior work has generally controlled only one of these dimensions at a time. We show that jointly tuning both decisions under a shared compute budget improves both reasoning quality and wall-clock training time. We instantiate this view as DUal-controlled tokEn allocaTion (DUET), a computationally efficient layer over GRPO that uses a lightweight pre-rollout surrogate of prompt informativeness to set how many rollouts each prompt receives, and a marker-gated abort rule with importance reweighting to set when to stop them. On Qwen3-1.7B trained on MATH, DUET outperforms full-budget GRPO and the other three budget-aware baseline methods. DUET's advantage further generalizes to other benchmarks across math and coding, and is on par with the best baseline on the scientific Q\&A domain, while also achieving a 1.62times wall-clock speedup. More notably, using only 50\% of the token budget, DUET still outperforms all baseline methods at their full budget, achieving an even higher 2.51times speedup over full-budget GRPO. We verify the high performance of DUET on other backbone LLMs, including Qwen3-4B and Llama-3.2-3B-Instruct. Notably, the gap between DUET and the strongest baseline widens as the budget tightens, contrary to the usual pattern in which efficient methods trade off quality as compute decreases. More broadly, these results suggest that DUET budget-aware control strategies are valuable not only for accelerating training, but also for improving the quality of the learning signal.

Test-time scaling has emerged as an effective approach for improving language model performance by utilizing additional compute at inference time. Recent studies have shown that overriding end-of-thinking tokens (e.g., replacing "</think>" with "Wait") can extend reasoning steps and improve accuracy. In this work, we explore whether a dedicated continue-thinking token can be learned to trigger extended reasoning. We augment a distilled version of DeepSeek-R1 with a single learned "<|continue-thinking|>" token, training only its embedding via reinforcement learning while keeping the model weights frozen. Our experiments show that this learned token achieves improved accuracy on standard math benchmarks compared to both the baseline model and a test-time scaling approach that uses a fixed token (e.g., "Wait") for budget forcing. In particular, we observe that in cases where the fixed-token approach enhances the base model's accuracy, our method achieves a markedly greater improvement. For example, on the GSM8K benchmark, the fixed-token approach yields a 1.3% absolute improvement in accuracy, whereas our learned-token method achieves a 4.2% improvement over the base model that does not use budget forcing.

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade effects where initial inconsistencies misguide the remaining generation. Existing revision strategies attempt to mitigate this by relying on static confidence scores, but these signals are inherently myopic; inconsistent tokens can appear confident to the model itself. We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision. Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations. We formalize revision as a robust optimization objective over context shifts and efficiently approximate this objective to prioritize unstable tokens for revision. On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, where models generate verbose and tangential reasoning traces even for simple queries. Recent works have tried to mitigate this by enforcing fixed token budgets, however, this can lead to underthinking, especially on harder problems. Through empirical analysis, we identify that this inefficiency often stems from unclear problem-solving strategies. To formalize this, we develop a theoretical model, BBAM (Bayesian Budget Allocation Model), which models reasoning as a sequence of sub-questions with varying uncertainty, and introduce the E^3 metric to capture the trade-off between correctness and computation efficiency. Building on theoretical results from BBAM, we propose Plan-and-Budget, a model-agnostic, test-time framework that decomposes complex queries into sub-questions and allocates token budgets based on estimated complexity using adaptive scheduling. Plan-and-Budget improves reasoning efficiency across a range of tasks and models, achieving up to +70% accuracy gains, -39% token reduction, and +187.5% improvement in E^3. Notably, it elevates a smaller model (DS-Qwen-32B) to match the efficiency of a larger model (DS-LLaMA-70B)-demonstrating Plan-and-Budget's ability to close performance gaps without retraining. Our code is available at anonymous.4open.science/r/P-and-B-6513/.

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse sampling or uniform pooling, blindly sacrifice fidelity by discarding decisive moments and wasting bandwidth on irrelevant backgrounds. We propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding. Tempo leverages a Small Vision-Language Model (SVLM) as a local temporal compressor, casting token reduction as an early cross-modal distillation process to generate compact, intent-aligned representations in a single forward pass. To enforce strict budgets without breaking causality, we introduce Adaptive Token Allocation (ATA). Exploiting the SVLM's zero-shot relevance prior and semantic front-loading, ATA acts as a training-free O(1) dynamic router. It allocates dense bandwidth to query-critical segments while compressing redundancies into minimal temporal anchors to maintain the global storyline. Extensive experiments show our 6B architecture achieves state-of-the-art performance with aggressive dynamic compression (0.5-16 tokens/frame). On the extreme-long LVBench (4101s), Tempo scores 52.3 under a strict 8K visual budget, outperforming GPT-4o and Gemini 1.5 Pro. Scaling to 2048 frames reaches 53.7. Crucially, Tempo compresses hour-long videos substantially below theoretical limits, proving true long-form video understanding relies on intent-driven efficiency rather than greedily padded context windows.

Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout engines, full-token updates can consume a large fraction of total training cost, turning token length into a hidden tax on RL. We introduce Not All Tokens Are Needed (NAT), a unified framework that makes the token budget a first-class optimization primitive. NAT updates the policy using only a selected subset of generated tokens while preserving the learning signal of full-sequence RL. The core idea is an unbiased partial-token policy-gradient estimator via Horvitz-Thompson reweighting, which ensures statistically correct gradients despite subsampling. We instantiate NAT with two simple, plug-and-play token selection schemes: Uniform Random Sampling (URS) and Random Prefix Cutting (RPC), both of which reduce forward and backward compute and memory without modifying the reward computation or rollout pipeline. Across mathematical reasoning benchmarks, NAT matches full-token GRPO performance while using as few as 50% of tokens, providing an efficient and orthogonal pathway to scaling RL beyond the limits imposed by long trajectories. In our experiments, RPC saves 18% peak GPU memory and 29% forward and backward RL training time for Qwen3-8B.

Forecasting is a critical task in decision-making across numerous domains. While historical numerical data provide a start, they fail to convey the complete context for reliable and accurate predictions. Human forecasters frequently rely on additional information, such as background knowledge and constraints, which can efficiently be communicated through natural language. However, in spite of recent progress with LLM-based forecasters, their ability to effectively integrate this textual information remains an open question. To address this, we introduce "Context is Key" (CiK), a time-series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities; crucially, every task in CiK requires understanding textual context to be solved successfully. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters, and propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark. Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings. This benchmark aims to advance multimodal forecasting by promoting models that are both accurate and accessible to decision-makers with varied technical expertise. The benchmark can be visualized at https://servicenow.github.io/context-is-key-forecasting/v0/.

AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-reads project files, re-derives prior decisions, and - most costly - may repeat debugging attempts that already failed. Reconstructing this context can consume an estimated 5,000-20,000 tokens per session; the bottleneck is often not model capability but missing project memory. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents. projectmem records development as an append-only, plain-text event log of typed events - issues, attempts, fixes, decisions, and notes - and deterministically projects that log into compact, AI-readable summaries served through the Model Context Protocol (MCP). Beyond storage, projectmem adds a deterministic pre-action gate that warns an agent before it repeats a previously failed fix or edits a known-fragile file. We frame this as Memory-as-Governance: memory that does not merely answer the agent but acts on its next action. The system runs fully offline with no telemetry; its immutable log also serves as a provenance trail for reproducible, auditable AI-assisted development. projectmem ships as a three-dependency Python package (14 MCP tools, 19 CLI commands, 37 automated tests) and is evaluated through a two-month self-study across 10 projects comprising 207 logged events. Source code: https://github.com/riponcm/projectmem.

Scaling the context size of large language models (LLMs) enables them to perform various new tasks, e.g., book summarization. However, the memory cost of the Key and Value (KV) cache in attention significantly limits the practical applications of LLMs. Recent works have explored token pruning for KV cache reduction in LLMs, relying solely on attention scores as a token importance indicator. However, our investigation into value vector norms revealed a notably non-uniform pattern questioning their reliance only on attention scores. Inspired by this, we propose a new method: Value-Aware Token Pruning (VATP) which uses both attention scores and the ell_{1} norm of value vectors to evaluate token importance. Extensive experiments on LLaMA2-7B-chat and Vicuna-v1.5-7B across 16 LongBench tasks demonstrate VATP's superior performance.

Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic memory construction that can be inefficient and may discard query-critical information. Although runtime memory utilization is a natural alternative, prior work often incurs substantial overhead and offers limited explicit control over the performance-cost trade-off. In this work, we present BudgetMem, a runtime agent memory framework for explicit, query-aware performance-cost control. BudgetMem structures memory processing as a set of memory modules, each offered in three budget tiers (i.e., Low/Mid/High). A lightweight router performs budget-tier routing across modules to balance task performance and memory construction cost, which is implemented as a compact neural policy trained with reinforcement learning. Using BudgetMem as a unified testbed, we study three complementary strategies for realizing budget tiers: implementation (method complexity), reasoning (inference behavior), and capacity (module model size). Across LoCoMo, LongMemEval, and HotpotQA, BudgetMem surpasses strong baselines when performance is prioritized (i.e., high-budget setting), and delivers better accuracy-cost frontiers under tighter budgets. Moreover, our analysis disentangles the strengths and weaknesses of different tiering strategies, clarifying when each axis delivers the most favorable trade-offs under varying budget regimes.

Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been a hot research topic. However, current algorithms such as sparse attention or key-value (KV) cache compression tend to use a fixed budget, which presents a significant challenge during deployment because it fails to account for the dynamic nature of real-world scenarios, where the optimal balance between accuracy and efficiency can vary greatly. In this paper, we find that borrowing top-p sampling (nucleus sampling) to sparse attention can surprisingly achieve adaptive budgeting. Based on this, we propose Twilight, a framework to bring adaptive sparsity to any existing sparse attention algorithm without sacrificing their accuracy. Empirical results show that Twilight can adaptively prune at most 98% of redundant tokens, leading to 15.4times acceleration in self-attention operations and 3.9times acceleration in end-to-end per token latency in long context LLM decoding.

While agents are increasingly spending more resources, today agent cost is mostly measured only after execution. A Budget-Aware Agent (BAGEN) should treat budget as an active control signal, rather than a passive cost metric. We first systematically define budget estimation as internal budgets (from agent computation) and external budgets (from agent actions). We then formalize budget-awareness as progressive interval estimation: at each step of a plan, an agent should predict an upper and lower bound on remaining budget, and alert when completion is unlikely. Scoring with a rollout-replay protocol, we find consistent failure patterns on four environments and five frontier agents: (1) strong agents do not necessarily have strong budget-awareness, with correlation r=0.35. (2) frontier models are consistently over-optimistic, continue spending on tasks that are unlikely to succeed, instead of alerting the user early. (3) budget-aware signal is actionable and trainable. Early stop saves 28-64% tokens on failed trajectories, and SFT+RL strengthens early stop and alert behavior. (4) precise interval calibration remains challenging, with interval coverage capping at 47% after SFT+RL. Project page: https://ragen-ai.github.io/bagen/

Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-1M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we load this trained KV cache, which we call a Cartridge, and decode a response. Critically, the cost of training a Cartridge can be amortized across all the queries referencing the same corpus. However, we find that the naive approach of training the Cartridge with next-token prediction on the corpus is not competitive with ICL. Instead, we propose self-study, a training recipe in which we generate synthetic conversations about the corpus and train the Cartridge with a context-distillation objective. We find that Cartridges trained with self-study replicate the functionality of ICL, while being significantly cheaper to serve. On challenging long-context benchmarks, Cartridges trained with self-study match ICL performance while using 38.6x less memory and enabling 26.4x higher throughput. Self-study also extends the model's effective context length (e.g. from 128k to 484k tokens on MTOB) and surprisingly, leads to Cartridges that can be composed at inference time without retraining.

In-context learning (ICL) is the standard method for low-resource classification, yet its efficacy in specialized domains remains largely unexplored. We address the challenge of classifying semantically complex, multi-party B2B conversations, where traditional ICL encounters significant limitations, especially as context length increases due to the concatenation of multiple few-shot examples. We introduce the Call Playbook dataset, featuring five classification tasks derived from real-world B2B conversations targeting core sales concepts. To bridge the gap between performance and practical utility, we propose novel knowledge extraction methods that distill verbose examples into compact, interpretable representations of structured classification criteria and precise task descriptions. Our approach achieves a 99\% reduction in token usage and improves macro-averaged AUC by up to 7\% over traditional ICL. Notably, it remains robust as context grows, unlike advanced token compression baselines which degrade by over 9 F1 points. Importantly, our framework enables direct refinement of classification logic, addressing critical needs for transparency, efficiency, and user interaction in real-world NLP applications.

Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they learn a new task from a few task demonstrations, without any parameter updates. This work examines the implications of in-context learning for the creation of datasets for new natural language tasks. Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by prompt retrieval that retrieves task examples from the annotated pool at test time. Based on this framework, we propose an unsupervised, graph-based selective annotation method, voke-k, to select diverse, representative examples to annotate. Extensive experiments on 10 datasets (covering classification, commonsense reasoning, dialogue, and text/code generation) demonstrate that our selective annotation method improves the task performance by a large margin. On average, vote-k achieves a 12.9%/11.4% relative gain under an annotation budget of 18/100, as compared to randomly selecting examples to annotate. Compared to state-of-the-art supervised finetuning approaches, it yields similar performance with 10-100x less annotation cost across 10 tasks. We further analyze the effectiveness of our framework in various scenarios: language models with varying sizes, alternative selective annotation methods, and cases where there is a test data domain shift. We hope that our studies will serve as a basis for data annotations as large language models are increasingly applied to new tasks. Our code is available at https://github.com/HKUNLP/icl-selective-annotation.

Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment imposes a fixed per-query token budget that varies across settings. Existing tree-search policies are largely budget-agnostic, treating the budget as a termination condition, which can lead to late-stage over-branching or premature termination. We propose {Budget-Guided MCTS} (BG-MCTS), a tree-search decoding algorithm that aligns its search policy with the remaining token budget: it starts with broad exploration, then prioritizes refinement and answer completion as the budget depletes while reducing late-stage branching from shallow nodes. BG-MCTS consistently outperforms budget-agnostic tree-search baselines across different budgets on MATH500 and AIME24/25 with open-weight LLMs.

Time series forecasting plays a vital role in supporting decision-making across a wide range of critical applications, including energy, healthcare, and finance. Despite recent advances, forecasting accuracy remains limited due to the challenge of integrating historical numerical sequences with contextual features, which often comprise unstructured textual data. To address this challenge, we propose TokenCast, an LLM-driven framework that leverages language-based symbolic representations as a unified intermediary for context-aware time series forecasting. Specifically, TokenCast employs a discrete tokenizer to transform continuous numerical sequences into temporal tokens, enabling structural alignment with language-based inputs. To bridge the semantic gap between modalities, both temporal and contextual tokens are embedded into a shared representation space via a pre-trained large language model (LLM), further optimized with autoregressive generative objectives. Building upon this unified semantic space, the aligned LLM is subsequently fine-tuned in a supervised manner to predict future temporal tokens, which are then decoded back into the original numerical space. Extensive experiments on diverse real-world datasets enriched with contextual features demonstrate the effectiveness and generalizability of TokenCast.

Providing Large Language Models with relevant contextual knowledge at inference time has been shown to greatly improve the quality of their generations. This is often achieved by prepending informative passages of text, or 'contexts', retrieved from external knowledge bases to their input. However, processing additional contexts online incurs significant computation costs that scale with their length. State Space Models (SSMs) offer a promising solution by allowing a database of contexts to be mapped onto fixed-dimensional states from which to start the generation. A key challenge arises when attempting to leverage information present across multiple contexts, since there is no straightforward way to condition generation on multiple independent states in existing SSMs. To address this, we leverage a simple mathematical relation derived from SSM dynamics to compose multiple states into one that efficiently approximates the effect of concatenating raw context tokens. Since the temporal ordering of contexts can often be uninformative, we enforce permutation-invariance by efficiently averaging states obtained via our composition algorithm across all possible context orderings. We evaluate our resulting method on WikiText and MSMARCO in both zero-shot and fine-tuned settings, and show that we can match the strongest performing baseline while enjoying on average 5.4x speedup.

The increasing context window size in Large Language Models (LLMs), such as the GPT and LLaMA series, has improved their ability to tackle complex, long-text tasks, but at the cost of inference efficiency, particularly regarding memory and computational complexity. Existing methods, including selective token retention and window-based attention, improve efficiency but risk discarding important tokens needed for future text generation. In this paper, we propose an approach that enhances LLM efficiency without token loss by reducing the memory and computational load of less important tokens, rather than discarding them.We address two challenges: 1) investigating the distribution of important tokens in the context, discovering recent tokens are more important than distant tokens in context, and 2) optimizing resources for distant tokens by sharing attention scores across layers. The experiments show that our method saves 35% KV cache without compromising the performance.

Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional evidence often declines. This leads to unnecessary token cost, higher latency, and noisier inputs for final report generation. We study marginal value estimation for context management in deep research agents and present the first systematic stage-aware comparison of pruning strategies across the pipeline. We evaluate lightweight heuristic criteria and a learned value model at pre-retrieval, post-retrieval, and pre-synthesis stages. Our results show that pruning effectiveness depends more on where pruning is applied than on the specific scoring rule: early pruning yields the largest end-to-end savings, while later pruning mainly refines the final synthesis context. Lightweight heuristics reduce token usage by up to 73% with little quality degradation, learned pruning remains competitive on selected trade-offs, and no single method dominates across quality, efficiency, and faithfulness. These findings provide practical guidance for designing efficient long-horizon agentic systems.

Question Answering (QA) in NLP is the task of finding answers to a query within a relevant context retrieved by a retrieval system. Yet, the mix of relevant and irrelevant information in these contexts can hinder performance enhancements in QA tasks. To address this, we introduce a context filtering approach that removes non-essential details, summarizing crucial content through Reward Modeling. This method emphasizes keeping vital data while omitting the extraneous during summarization model training. We offer a framework for developing efficient QA models by discerning useful information from dataset pairs, bypassing the need for costly human evaluation. Furthermore, we show that our approach can significantly outperform the baseline, as evidenced by a 6.8-fold increase in the EM Per Token (EPT) metric, which we propose as a measure of token efficiency, indicating a notable token-efficiency boost for low-resource settings.

Thousands of diverse benchmarks have been developed to measure the quality of large language models (LLMs). Yet prior work has demonstrated that LLM performance is often sufficiently explained by a small set of latent factors, or abilities. This suggests the potential for more efficient and principled benchmarking, but it remains difficult to compare the quality of different methods. Motivated by predictive validity, we argue that the quality of a benchmarking framework should be grounded in how efficiently it enables the prediction of model performance on unseen tasks. To analyze this objective, we collect the "Wide-scale Item Level Dataset" (WILD), a dataset of item-model response pairs, comprising evaluations of 65 models on 109,564 unique items spanning 163 tasks drawn from 27 datasets. This dataset enables the first analysis of how different techniques can predict a model's performance on a large, diverse collection of unseen tasks under different budget constraints. We demonstrate that combining a modified multidimensional item response theory (IRT) model with adaptive item selection driven by optimal experimental design can predict performance on 112 held-out benchmark tasks with a mean absolute error (MAE) of less than 7%, and can do so after observing only 16 items. We further demonstrate that incorporating cost-aware discount factors into our selection criteria can reduce the total tokens needed to reach 7% MAE from 141,000 tokens to only 22,000, an 85% reduction in evaluation cost.

Government fiscal policies, particularly annual union budgets, exert significant influence on financial markets. However, real-time analysis of budgetary impacts on sector-specific equity performance remains methodologically challenging and largely unexplored. This study proposes a framework to systematically identify and rank sectors poised to benefit from India's Union Budget announcements. The framework addresses two core tasks: (1) multi-label classification of excerpts from budget transcripts into 81 predefined economic sectors, and (2) performance ranking of these sectors. Leveraging a comprehensive corpus of Indian Union Budget transcripts from 1947 to 2025, we introduce BASIR (Budget-Assisted Sectoral Impact Ranking), an annotated dataset mapping excerpts from budgetary transcripts to sectoral impacts. Our architecture incorporates fine-tuned embeddings for sector identification, coupled with language models that rank sectors based on their predicted performances. Our results demonstrate 0.605 F1-score in sector classification, and 0.997 NDCG score in predicting ranks of sectors based on post-budget performances. The methodology enables investors and policymakers to quantify fiscal policy impacts through structured, data-driven insights, addressing critical gaps in manual analysis. The annotated dataset has been released under CC-BY-NC-SA-4.0 license to advance computational economics research.

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing Omni-LLM pruning methods typically reduce this cost by selecting tokens that are important for the current query or strongly aligned with cross-modal cues. However, such strategies can discard evidence that falls outside these criteria, even when needed for different questions or for understanding context beyond aligned audio-visual cues. To address this limitation, we reframe Omni-LLM token reduction as preserving broad audio-visual context while removing cross-modal redundancy. We propose ContextGuard, an inference-time token pruning framework built on this principle. ContextGuard predicts coarse visual semantics from audio and prunes video tokens whose coarse semantics are likely recoverable from audio, while retaining additional video tokens to preserve localized visual details that audio alone cannot specify. For further compression, our method merges temporally similar video tokens. The framework requires no downstream LLM fine-tuning and uses only an independently trained lightweight predictor. On Qwen2.5-Omni and Video-SALMONN2+ at 3B and 7B scales across six audio-visual benchmarks, ContextGuard outperforms prior inference-time pruning methods while pruning more tokens. Notably, on Qwen2.5-Omni 7B, ContextGuard achieves full-token-level performance on five of six benchmarks while pruning 55% of input tokens.

Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue that the bottleneck lies not in how post-encoding representations are compressed but in the volume of pixels the encoder receives, and address it with ResAdapt, an Input-side adaptation framework that learns how much visual budget each frame should receive before encoding. ResAdapt couples a lightweight Allocator with an unchanged MLLM backbone, so the backbone retains its native visual-token interface while receiving an operator-transformed input. We formulate allocation as a contextual bandit and train the Allocator with Cost-Aware Policy Optimization (CAPO), which converts sparse rollout feedback into a stable accuracy-cost learning signal. Across budget-controlled video QA, temporal grounding, and image reasoning tasks, ResAdapt improves low-budget operating points and often lies on or near the efficiency-accuracy frontier, with the clearest gains on reasoning-intensive benchmarks under aggressive compression. Notably, ResAdapt supports up to 16x more frames at the same visual budget while delivering over 15% performance gain. Code is available at https://github.com/Xnhyacinth/ResAdapt.

Providing external knowledge to Large Language Models (LLMs) is a key point for using these models in real-world applications for several reasons, such as incorporating up-to-date content in a real-time manner, providing access to domain-specific knowledge, and contributing to hallucination prevention. The vector database-based Retrieval Augmented Generation (RAG) approach has been widely adopted to this end. Thus, any part of external knowledge can be retrieved and provided to some LLM as the input context. Despite RAG approach's success, it still might be unfeasible for some applications, because the context retrieved can demand a longer context window than the size supported by LLM. Even when the context retrieved fits into the context window size, the number of tokens might be expressive and, consequently, impact costs and processing time, becoming impractical for most applications. To address these, we propose CRAG, a novel approach able to effectively reduce the number of prompting tokens without degrading the quality of the response generated compared to a solution using RAG. Through our experiments, we show that CRAG can reduce the number of tokens by at least 46\%, achieving more than 90\% in some cases, compared to RAG. Moreover, the number of tokens with CRAG does not increase considerably when the number of reviews analyzed is higher, unlike RAG, where the number of tokens is almost 9x higher when there are 75 reviews compared to 4 reviews.

Large Language Models (LLMs) have revolutionized a wide range of domains such as natural language processing, computer vision, and multi-modal tasks due to their ability to comprehend context and perform logical reasoning. However, the computational and memory demands of LLMs, particularly during inference, pose significant challenges when scaling them to real-world, long-context, and real-time applications. Key-Value (KV) cache management has emerged as a critical optimization technique for accelerating LLM inference by reducing redundant computations and improving memory utilization. This survey provides a comprehensive overview of KV cache management strategies for LLM acceleration, categorizing them into token-level, model-level, and system-level optimizations. Token-level strategies include KV cache selection, budget allocation, merging, quantization, and low-rank decomposition, while model-level optimizations focus on architectural innovations and attention mechanisms to enhance KV reuse. System-level approaches address memory management, scheduling, and hardware-aware designs to improve efficiency across diverse computing environments. Additionally, the survey provides an overview of both text and multimodal datasets and benchmarks used to evaluate these strategies. By presenting detailed taxonomies and comparative analyses, this work aims to offer useful insights for researchers and practitioners to support the development of efficient and scalable KV cache management techniques, contributing to the practical deployment of LLMs in real-world applications. The curated paper list for KV cache management is in: https://github.com/TreeAI-Lab/Awesome-KV-Cache-Management{https://github.com/TreeAI-Lab/Awesome-KV-Cache-Management}.

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training with potential for strong performance gains. In this paper, we formally define the problem and identify three key challenges: (1) inefficient training due to excessive reasoning steps, (2) disregard of the imbalanced token entropy distribution, and (3) underutilization of token information. To address these challenges, we propose RMT, a framework for efficient, adaptive, and unified reinforcement mid-training with various innovative components. In particular, we first introduce a dynamic token budget mechanism that constrains unnecessary reasoning steps and mitigates model overthinking. Next, we design a curriculum-based adaptive sampling method that fosters a progressive learning trajectory from easy to hard tokens. Finally, we present a dual training strategy that combines reinforcement learning with next-token prediction, ensuring targeted learning on key tokens and full exploitation of all token information. Extensive experiments demonstrate the superiority of RMT over state-of-the-art methods, achieving up to +64.91% performance improvement with only 21% of the reasoning length in language modeling. We also show that checkpoints obtained after reinforcement mid-training can benefit the subsequent post-training, yielding up to +18.76% improvement in the mathematical domain.

In recent years, general visual foundation models (VFMs) have witnessed increasing adoption, particularly as image encoders for popular multi-modal large language models (MLLMs). However, without semantically fine-grained supervision, these models still encounter fundamental prediction errors in the context of downstream text-image-related tasks, i.e., perception, understanding and reasoning with images containing small and dense texts. To bridge this gap, we develop TokenOCR, the first token-level visual foundation model specifically tailored for text-image-related tasks, designed to support a variety of traditional downstream applications. To facilitate the pretraining of TokenOCR, we also devise a high-quality data production pipeline that constructs the first token-level image text dataset, TokenIT, comprising 20 million images and 1.8 billion token-mask pairs. Furthermore, leveraging this foundation with exceptional image-as-text capability, we seamlessly replace previous VFMs with TokenOCR to construct a document-level MLLM, TokenVL, for VQA-based document understanding tasks. Finally, extensive experiments demonstrate the effectiveness of TokenOCR and TokenVL. Code, datasets, and weights will be available at https://token-family.github.io/TokenOCR_project.

Long context inference presents challenges at the system level with increased compute and memory requirements, as well as from an accuracy perspective in being able to reason over long contexts. Recently, several methods have been proposed to compress the prompt to reduce the context length. However, there has been little work on comparing the different proposed methods across different tasks through a standardized analysis. This has led to conflicting results. To address this, here we perform a comprehensive characterization and evaluation of different prompt compression methods. In particular, we analyze extractive compression, summarization-based abstractive compression, and token pruning methods. Surprisingly, we find that extractive compression often outperforms all the other approaches, and enables up to 10x compression with minimal accuracy degradation. Interestingly, we also find that despite several recent claims, token pruning methods often lag behind extractive compression. We only found marginal improvements on summarization tasks.

We present TokenVerse -- a method for multi-concept personalization, leveraging a pre-trained text-to-image diffusion model. Our framework can disentangle complex visual elements and attributes from as little as a single image, while enabling seamless plug-and-play generation of combinations of concepts extracted from multiple images. As opposed to existing works, TokenVerse can handle multiple images with multiple concepts each, and supports a wide-range of concepts, including objects, accessories, materials, pose, and lighting. Our work exploits a DiT-based text-to-image model, in which the input text affects the generation through both attention and modulation (shift and scale). We observe that the modulation space is semantic and enables localized control over complex concepts. Building on this insight, we devise an optimization-based framework that takes as input an image and a text description, and finds for each word a distinct direction in the modulation space. These directions can then be used to generate new images that combine the learned concepts in a desired configuration. We demonstrate the effectiveness of TokenVerse in challenging personalization settings, and showcase its advantages over existing methods. project's webpage in https://token-verse.github.io/

Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive computational and memory costs, limiting the practicality of long-context LLMs. In this work, we take a different perspective-visual context scaling-to tackle this challenge. Instead of extending token-based sequences, we propose Glyph, a framework that renders long texts into images and processes them with vision-language models (VLMs). This approach substantially compresses textual input while preserving semantic information, and we further design an LLM-driven genetic search to identify optimal visual rendering configurations for balancing accuracy and compression. Through extensive experiments, we demonstrate that our method achieves 3-4x token compression while maintaining accuracy comparable to leading LLMs such as Qwen3-8B on various long-context benchmarks. This compression also leads to around 4x faster prefilling and decoding, and approximately 2x faster SFT training. Furthermore, under extreme compression, a 128K-context VLM could scale to handle 1M-token-level text tasks. In addition, the rendered text data benefits real-world multimodal tasks, such as document understanding. Our code and model are released at https://github.com/thu-coai/Glyph.