Daily Papers

Retrieval-Augmented Generation (RAG) has emerged as the predominant paradigm for grounding Large Language Model outputs in factual knowledge, effectively mitigating hallucinations. However, conventional RAG systems operate under a "retrieve-always" assumption, querying vector databases for every input regardless of query complexity. This static approach incurs substantial computational overhead and inference latency, particularly problematic for high-throughput production deployments. We introduce L-RAG (Lazy Retrieval-Augmented Generation), an adaptive framework that implements hierarchical context management through entropy-based gating. L-RAG employs a two-tier architecture: queries are first processed with a compact document summary, and expensive chunk retrieval is triggered only when the model's predictive entropy exceeds a calibrated threshold, signaling genuine uncertainty. Through experiments on SQuAD 2.0 (N=500) using the Phi-2 model, we demonstrate that L-RAG provides a tunable accuracy-efficiency trade-off: at a conservative threshold (tau=0.5), L-RAG achieves 78.2% accuracy, matching Standard RAG (77.8%), with 8% retrieval reduction; at a balanced threshold (tau=1.0), retrieval reduction increases to 26% with modest accuracy trade-off (76.0%). Latency analysis shows that L-RAG saves 80-210ms per query when retrieval latency exceeds 500ms. Analysis of entropy distributions reveals statistically significant separation (p < 0.001) between correct predictions (H=1.72) and errors (H=2.20), validating entropy as a reliable uncertainty signal. L-RAG offers a practical, training-free approach toward more efficient RAG deployment, providing system architects with a configurable knob to balance accuracy and throughput requirements.

The rapid expansion of capabilities in Large Language Model (LLM) agents has exposed a critical architectural bottleneck: when agents are given access to a flat, monolithic registry of tools, the model must evaluate hundreds or thousands of options simultaneously. This leads to decision-space explosion, context window saturation, and degraded routing accuracy. To address these limitations, this paper presents a hierarchical, skill-based architecture for agentic orchestration. Capabilities are organized as a rooted tree where internal nodes make routing decisions and leaf nodes execute deterministic tasks. The runtime enforces a single-step execution loop governed by a Last-In-First-Out (LIFO) stack, giving the agent a form of memory akin to a Pushdown Automaton, therefore enabling it to track nested execution contexts and resume deterministically from any depth. Capability discovery follows a manifest-driven, lazy-loading protocol: only the immediate children of the active node are loaded, so memory and prompt costs scale with the explored path rather than the global registry. By replacing global memory with localized stack frames, the architecture prevents outputs from one execution branch from leaking into another, establishing the isolation guarantees required for deployment in regulated enterprise environments. We also discuss UPI Help, an AI-powered digital payments support product, as a motivating production deployment context. We provide a mathematical formalization of the orchestration state, detailed algorithmic analysis of the execution loop, and controlled benchmarks comparing flat and hierarchical routing under increasing tool catalogs, multi-step workflow pressure, and visible schema-token exposure per LLM call.

In the rapidly evolving landscape of digital twins (DT) and 6G networks, the integration of large language models (LLMs) presents a novel approach to network management. This paper explores the application of LLMs in managing 6G-empowered DT networks, with a focus on optimizing data retrieval and communication efficiency in smart city scenarios. The proposed framework leverages LLMs for intelligent DT problem analysis and radio resource management (RRM) in fully autonomous way without any manual intervention. Our proposed framework -- LINKs, builds up a lazy loading strategy which can minimize transmission delay by selectively retrieving the relevant data. Based on the data retrieval plan, LLMs transform the retrieval task into an numerical optimization problem and utilizing solvers to build an optimal RRM, ensuring efficient communication across the network. Simulation results demonstrate the performance improvements in data planning and network management, highlighting the potential of LLMs to enhance the integration of DT and 6G technologies.

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

Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as each denoising step requires running the whole transformer model with a large amount of parameters. In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps. Furthermore, we show that the lower bound of similarity between outputs at consecutive steps is notably high, and this similarity can be linearly approximated using the inputs. To verify our demonstrations, we propose the LazyDiT, a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations. Specifically, we incorporate lazy learning layers into the model, effectively trained to maximize laziness, enabling dynamic skipping of redundant computations. Experimental results show that LazyDiT outperforms the DDIM sampler across multiple diffusion transformer models at various resolutions. Furthermore, we implement our method on mobile devices, achieving better performance than DDIM with similar latency. Code: https://github.com/shawnricecake/lazydit

The inference of transformer-based large language models consists of two sequential stages: 1) a prefilling stage to compute the KV cache of prompts and generate the first token, and 2) a decoding stage to generate subsequent tokens. For long prompts, the KV cache must be computed for all tokens during the prefilling stage, which can significantly increase the time needed to generate the first token. Consequently, the prefilling stage may become a bottleneck in the generation process. An open question remains whether all prompt tokens are essential for generating the first token. To answer this, we introduce a novel method, LazyLLM, that selectively computes the KV for tokens important for the next token prediction in both the prefilling and decoding stages. Contrary to static pruning approaches that prune the prompt at once, LazyLLM allows language models to dynamically select different subsets of tokens from the context in different generation steps, even though they might be pruned in previous steps. Extensive experiments on standard datasets across various tasks demonstrate that LazyLLM is a generic method that can be seamlessly integrated with existing language models to significantly accelerate the generation without fine-tuning. For instance, in the multi-document question-answering task, LazyLLM accelerates the prefilling stage of the LLama 2 7B model by 2.34x while maintaining accuracy.

While Multimodal Large Language Models (MLLMs) excel in cross-modal reasoning, they often struggle to perceive fine-grained details in complex high-resolution images. Recent training-free methods address this through image scaling and localized cropping. However, applying these manipulations indiscriminately introduces computational redundancy for simple queries and can degrade accuracy by truncating essential global context or introducing irrelevant background noise. To this end, we propose LazyMCoT, a dynamic and training-free framework that adaptively allocates visual grounding efforts based on sample difficulty. The framework features an Adaptive Routing mechanism that evaluates predictive uncertainty using first-token statistics from a single forward pass. This efficiently bypasses confident cases while ensuring the recall of difficult samples via conformal calibration. For these challenging cases, a Collaborative Grounding module integrates the inherent cross-modal attention of the model with an external visual expert through a two-stage refinement process. This refinement process generates a precise localized display to recover small or occluded targets. Extensive experiments across diverse benchmarks demonstrate that LazyMCoT rivals training-based approaches by simultaneously improving reasoning accuracy and reducing average inference latency. Our code is availble at https://github.com/TencentBAC/LazyMCoT.

Large Language Models (LLMs) exhibit enhanced reasoning capabilities by employing Chain-of-Thought (CoT). However, the extended reasoning sequences introduce significant GPU memory overhead due to increased key-value (KV) cache size, particularly in tasks requiring long reasoning sequences, such as mathematics and programming. Existing KV cache compression methods mitigate memory bottlenecks but struggle in long reasoning tasks. In this paper, we analyze attention patterns in reasoning tasks and reveal a Token Importance Recurrence phenomenon: a large proportion of tokens receive renewed attention after multiple decoding steps, which is failed to capture by existing works and may lead to unpredictable eviction on such periodically critical tokens. To address this, we propose LazyEviction, a lagged KV eviction framework designed to maintain reasoning performance while reducing KV memory. LazyEviction is an Observation Window-based Lagged Eviction Mechanism retaining latent recurring tokens by performing lagged evictions across decoding steps, which contains two key components: (1) Recurrence Interval Tracking for capturing temporal variations in token importance, and (2) an Maximum Recurrence Interval-Centric Eviction Policy that prioritizes eviction based on tokens' recurrence patterns. Extensive experiments demonstrate that LazyEviction reduces KV cache size by 50% while maintaining comparable accuracy on mathematics reasoning datasets, outperforming state-of-the-art methods. Our findings highlight the importance of preserving recurring tokens, which are critical for maintaining knowledge continuity in multi-step reasoning tasks.

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks dynamically. When managed inefficiently, this memory can be significantly wasted by fragmentation and redundant duplication, limiting the batch size. To address this problem, we propose PagedAttention, an attention algorithm inspired by the classical virtual memory and paging techniques in operating systems. On top of it, we build vLLM, an LLM serving system that achieves (1) near-zero waste in KV cache memory and (2) flexible sharing of KV cache within and across requests to further reduce memory usage. Our evaluations show that vLLM improves the throughput of popular LLMs by 2-4times with the same level of latency compared to the state-of-the-art systems, such as FasterTransformer and Orca. The improvement is more pronounced with longer sequences, larger models, and more complex decoding algorithms. vLLM's source code is publicly available at https://github.com/vllm-project/vllm

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms of resource and latency requirements, as a result of the diverse applications and the dynamic execution nature of LLMs. Existing systems are fundamentally limited in handling these characteristics and cause problems such as severe queuing delays, poor tail latencies, and SLO violations. We introduce Llumnix, an LLM serving system that reacts to such heterogeneous and unpredictable requests by runtime rescheduling across multiple model instances. Similar to context switching across CPU cores in modern operating systems, Llumnix reschedules requests to improve load balancing and isolation, mitigate resource fragmentation, and differentiate request priorities and SLOs. Llumnix implements the rescheduling with an efficient and scalable live migration mechanism for requests and their in-memory states, and exploits it in a dynamic scheduling policy that unifies the multiple rescheduling scenarios elegantly. Our evaluations show that Llumnix improves tail latencies by an order of magnitude, accelerates high-priority requests by up to 1.5x, and delivers up to 36% cost savings while achieving similar tail latencies, compared against state-of-the-art LLM serving systems. Llumnix is publicly available at https://github.com/AlibabaPAI/llumnix.

Current LLM-based coding agents follow a serial execution paradigm: the model first generates the complete code, then invokes an interpreter to execute it. This sequential workflow leaves the executor idle during generation and the generator idle during execution, resulting in unnecessary end-to-end latency. We observe that, unlike human developers, LLMs produce code tokens sequentially without revision, making it possible to execute code as it is being generated. We formalize this parallel execution paradigm, modeling it as a three-stage pipeline of generation, detection, and execution, and derive closed-form latency bounds that characterize its speedup potential and operating regimes. We then present Eager, a concrete implementation featuring AST-based chunking, dynamic batching with gated execution, and early error interruption. We evaluate Eager across four benchmarks, seven LLMs, and three execution environments. Results show that Eager reduces the non-overlapped execution latency by up to 99.9% and the end-to-end latency by up to 55% across seven LLMs and four benchmarks.

LLMs have seen rapid adoption in all domains. They need to be trained on high-end high-performance computing (HPC) infrastructures and ingest massive amounts of input data. Unsurprisingly, at such a large scale, unexpected events (e.g., failures of components, instability of the software, undesirable learning patterns, etc.), are frequent and typically impact the training in a negative fashion. Thus, LLMs need to be checkpointed frequently so that they can be rolled back to a stable state and subsequently fine-tuned. However, given the large sizes of LLMs, a straightforward checkpointing solution that directly writes the model parameters and optimizer state to persistent storage (e.g., a parallel file system), incurs significant I/O overheads. To address this challenge, in this paper we study how to reduce the I/O overheads for enabling fast and scalable checkpointing for LLMs that can be applied at high frequency (up to the granularity of individual iterations) without significant impact on the training process. Specifically, we introduce a lazy asynchronous multi-level approach that takes advantage of the fact that the tensors making up the model and optimizer state shards remain immutable for extended periods of time, which makes it possible to copy their content in the background with minimal interference during the training process. We evaluate our approach at scales of up to 180 GPUs using different model sizes, parallelism settings, and checkpointing frequencies. The results show up to 48times faster checkpointing and 2.2times faster end-to-end training runtime compared with the state-of-art checkpointing approaches.

LLM serving systems process heterogeneous query workloads where different categories exhibit different characteristics. Code queries cluster densely in embedding space while conversational queries distribute sparsely. Content staleness varies from minutes (stock data) to months (code patterns). Query repetition patterns range from power-law (code) to uniform (conversation), producing long tail cache hit rate distributions: high-repetition categories achieve 40-60% hit rates while low-repetition or volatile categories achieve 5-15% hit rates. Vector databases must exclude the long tail because remote search costs (30ms) require 15--20% hit rates to break even, leaving 20-30% of production traffic uncached. Uniform cache policies compound this problem: fixed thresholds cause false positives in dense spaces and miss valid paraphrases in sparse spaces; fixed TTLs waste memory or serve stale data. This paper presents category-aware semantic caching where similarity thresholds, TTLs, and quotas vary by query category. We present a hybrid architecture separating in-memory HNSW search from external document storage, reducing miss cost from 30ms to 2ms. This reduction makes low-hit-rate categories economically viable (break-even at 3-5% versus 15-20%), enabling cache coverage across the entire workload distribution. Adaptive load-based policies extend this framework to respond to downstream model load, dynamically adjusting thresholds and TTLs to reduce traffic to overloaded models by 9-17% in theoretical projections.

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large transformer backbones, we explore transitioning transformer models into hybrid architectures for a more efficient generation. In this work, we propose LightTransfer, a lightweight method that transforms models such as LLaMA into hybrid variants. Our approach identifies lazy layers -- those focusing on recent or initial tokens -- and replaces their full attention with streaming attention. This transformation can be performed without any training for long-context understanding tasks or with minimal fine-tuning for o1-like long reasoning generation tasks that require stronger reasoning capabilities. Experiments across diverse benchmarks and models (e.g., LLaMA, Mistral, QwQ-STILL) demonstrate that, even when half of the layers are identified as lazy, LightTransfer achieves up to 2.17times throughput improvement with minimal performance loss (<1.5% on LongBench) and achieves 53.3\% on math benchmark AIME24 of advanced o1-like long reasoning model QwQ-STILL.

Large language models (LLMs) have shown remarkable progress in code generation, but their generated code often suffers from inefficiency, resulting in longer execution times and higher memory consumption. To address this issue, we propose EffiLearner, a self-optimization framework that utilizes execution overhead profiles to improve the efficiency of LLM-generated code. EffiLearner first generates code using an LLM, then executes it locally to capture execution time and memory usage profiles. These profiles are fed back to the LLM, which then revises the code to reduce overhead. To evaluate the effectiveness of EffiLearner, we conduct extensive experiments on the EffiBench, HumanEval, and MBPP with 16 open-source and 6 closed-source models. Our evaluation results demonstrate that through iterative self-optimization, EffiLearner significantly enhances the efficiency of LLM-generated code. For example, the execution time (ET) of StarCoder2-15B for the EffiBench decreases from 0.93 (s) to 0.12 (s) which reduces 87.1% the execution time requirement compared with the initial code. The total memory usage (TMU) of StarCoder2-15B also decreases from 22.02 (Mb*s) to 2.03 (Mb*s), which decreases 90.8% of total memory consumption during the execution process. The source code of EffiLearner was released in https://github.com/huangd1999/EffiLearner

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual sub-procedures, e.g. local inference and communication, however, there is no comprehensive framework that provides a holistic system view for optimizing LLM serving in an end-to-end manner. In this work, we conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. Our analysis reveals that a comprehensive LLM serving endpoint must address a series of efficiency bottlenecks that extend beyond LLM inference. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving. Our extensive experiments reveal that with 64 concurrent requests, ScaleLLM achieves a 4.3x speed up over vLLM and outperforms state-of-the-arts with 1.5x higher throughput.

Many LLM tasks are performed in large batches or even offline, and the performance indictor for which is throughput. These tasks usually show the characteristic of prefix sharing, where different prompt input can partially show the common prefix. However, the existing LLM inference engines tend to optimize the streaming requests and show limitations of supporting the large batched tasks with the prefix sharing characteristic. The existing solutions use the LRU-based cache to reuse the KV context of common prefix. The KV context that is about to be reused may prematurely be evicted with the implicit cache management. Even if not evicted, the lifetime of the shared KV context is extended since requests sharing the same context are not scheduled together, resulting in larger memory usage. These streaming oriented systems schedule the requests in the first-come-first-serve or similar order. As a result, the requests with larger ratio of decoding steps may be scheduled too late to be able to mix with the prefill chunks to increase the hardware utilization. Besides, the token and request number based batching can limit the size of token-batch, which keeps the GPU from saturating for the iterations dominated by decoding tokens. We propose BatchLLM to address the above problems. BatchLLM explicitly identifies the common prefixes globally. The requests sharing the same prefix will be scheduled together to reuse the KV context the best, which also shrinks the lifetime of common KV memory. BatchLLM reorders the requests and schedules the requests with larger ratio of decoding first to better mix the decoding tokens with the latter prefill chunks and applies memory-centric token batching to enlarge the token-batch sizes, which helps to increase the GPU utilization. Extensive evaluation shows that BatchLLM outperforms vLLM by 1.1x to 2x on a set of microbenchmarks and two typical industry workloads.

Pharo offers a sophisticated completion engine based on semantic heuristics, which coordinates specific fetchers within a lazy architecture. These heuristics can be recomposed to support various activities (e.g., live programming or history usage navigation). While this system is powerful, it does not account for the repository structure when suggesting global names such as class names, class variables, or global variables. As a result, it does not prioritize classes within the same package or project, treating all global names equally. In this paper, we present a new heuristic that addresses this limitation. Our approach searches variable names in a structured manner: it begins with the package of the requesting class, then expands to other packages within the same repository, and finally considers the global namespace. We describe the logic behind this heuristic and evaluate it against the default semantic heuristic and one that directly queries the global namespace. Preliminary results indicate that the Mean Reciprocal Rank (MRR) improves, confirming that package-awareness completions deliver more accurate and relevant suggestions than the previous flat global approach.

Tool calling has become increasingly popular for Large Language Models (LLMs). However, for large tool sets, the resulting tokens would exceed the LLM's context window limit, making it impossible to include every tool. Hence, an external retriever is used to provide LLMs with the most relevant tools for a query. Existing retrieval models rank tools based on the similarity between a user query and a tool description (TD). This leads to suboptimal retrieval as user requests are often poorly aligned with the language of TD. To remedy the issue, we propose ToolDreamer, a framework to condition retriever models to fetch tools based on hypothetical (synthetic) TD generated using an LLM, i.e., description of tools that the LLM feels will be potentially useful for the query. The framework enables a more natural alignment between queries and tools within the language space of TD's. We apply ToolDreamer on the ToolRet dataset and show that our method improves the performance of sparse and dense retrievers with and without training, thus showcasing its flexibility. Through our proposed framework, our aim is to offload a portion of the reasoning burden to the retriever so that the LLM may effectively handle a large collection of tools without inundating its context window.

The reliance on implicit point matching via attention has become a core bottleneck in drag-based editing, resulting in a fundamental compromise on weakened inversion strength and costly test-time optimization (TTO). This compromise severely limits the generative capabilities of diffusion models, suppressing high-fidelity inpainting and text-guided creation. In this paper, we introduce LazyDrag, the first drag-based image editing method for Multi-Modal Diffusion Transformers, which directly eliminates the reliance on implicit point matching. In concrete terms, our method generates an explicit correspondence map from user drag inputs as a reliable reference to boost the attention control. This reliable reference opens the potential for a stable full-strength inversion process, which is the first in the drag-based editing task. It obviates the necessity for TTO and unlocks the generative capability of models. Therefore, LazyDrag naturally unifies precise geometric control with text guidance, enabling complex edits that were previously out of reach: opening the mouth of a dog and inpainting its interior, generating new objects like a ``tennis ball'', or for ambiguous drags, making context-aware changes like moving a hand into a pocket. Additionally, LazyDrag supports multi-round workflows with simultaneous move and scale operations. Evaluated on the DragBench, our method outperforms baselines in drag accuracy and perceptual quality, as validated by VIEScore and human evaluation. LazyDrag not only establishes new state-of-the-art performance, but also paves a new way to editing paradigms.

With the widespread adoption of Large Language Models (LLMs), serving LLM inference requests has become an increasingly important task, attracting active research advancements. Practical workloads play an essential role in this process: they are critical for motivating and benchmarking serving techniques and systems. However, the existing understanding of real-world LLM serving workloads is limited due to the lack of a comprehensive workload characterization. Prior analyses remain insufficient in scale and scope, thus failing to fully capture intricate workload characteristics. In this paper, we fill the gap with an in-depth characterization of LLM serving workloads collected from our worldwide cloud inference serving service, covering not only language models but also emerging multimodal and reasoning models, and unveiling important new findings in each case. Moreover, based on our findings, we propose ServeGen, a principled framework for generating realistic LLM serving workloads by composing them on a per-client basis. A practical use case in production validates that ServeGen avoids 50% under-provisioning compared to naive workload generation, demonstrating ServeGen's advantage in performance benchmarking. We will open-source ServeGen to foster future research.

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing serving strategies often employ fixed model scales or static two-stage speculative decoding, failing to dynamically adapt to the varying complexities of user requests or fluctuations in system performance. This paper introduces , a novel framework that reimagines LLM inference as an adaptive routing problem solved through multi-level speculative decoding. dynamically constructs and optimizes inference "paths" (chains of models) based on real-time feedback, addressing the limitations of static approaches. Our contributions are threefold: (1) An adaptive model chain scheduling mechanism that leverages performance profiling (execution times) and predictive similarity metrics (derived from token distribution divergence) to continuously select the optimal sequence of draft and verifier models, minimizing predicted latency per generated token. (2) A multi-level collaborative verification framework where intermediate models within the selected chain can validate speculative tokens, reducing the verification burden on the final, most powerful target model. (3) A synchronized state management system providing efficient, consistent KV cache handling across heterogeneous models in the chain, including precise, low-overhead rollbacks tailored for asynchronous batch processing inherent in multi-level speculation. Preliminary experiments demonstrate the validity of our method.

While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of LLMs, function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting without fine-tuning. This paper proposes a simple yet controllable target-driven approach called Reverse Chain to empower LLMs with capabilities to use external APIs with only prompts. Given that most open-source LLMs have limited tool-use or tool-plan capabilities, LLMs in Reverse Chain are only employed to implement simple tasks, e.g., API selection and argument completion, and a generic rule is employed to implement a controllable multiple functions calling. In this generic rule, after selecting a final API to handle a given task via LLMs, we first ask LLMs to fill the required arguments from user query and context. Some missing arguments could be further completed by letting LLMs select another API based on API description before asking user. This process continues until a given task is completed. Extensive numerical experiments indicate an impressive capability of Reverse Chain on implementing multiple function calling. Interestingly enough, the experiments also reveal that tool-use capabilities of the existing LLMs, e.g., ChatGPT, can be greatly improved via Reverse Chain.

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed decreases significantly as the sequence length grows. This slowdown is primarily caused by loading a large KV cache during self-attention. Previous works have shown that a small portion of critical tokens will dominate the attention outcomes. However, we observe the criticality of a token highly depends on the query. To this end, we propose Quest, a query-aware KV cache selection algorithm. Quest keeps track of the minimal and maximal Key values in KV cache pages and estimates the criticality of a given page using Query vectors. By only loading the Top-K critical KV cache pages for attention, Quest significantly speeds up self-attention without sacrificing accuracy. We show that Quest can achieve up to 2.23x self-attention speedup, which reduces inference latency by 7.03x while performing well on tasks with long dependencies with negligible accuracy loss. Code is available at http://github.com/mit-han-lab/Quest .

Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate generation modules (a.k.a. generators). As such, generators' performance largely depends on the effectiveness and efficiency of retrievers. However, the retrieval paradigm that we design and use remains flat, which treats the retrieval procedures as a one-off deal with constant granularity. Despite effectiveness, we argue that they suffer from two limitations: (1) flat retrieval exerts a significant burden on one retriever; (2) constant granularity limits the ceiling of retrieval performance. In this work, we propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency. Specifically, FunnelRAG establishes a progressive retrieval pipeline by collaborating coarse-to-fine granularity, large-to-small quantity, and low-to-high capacity, which can relieve the burden on one retriever and also promote the ceiling of retrieval performance. Extensive experiments manifest that FunnelRAG achieves comparable retrieval performance while the time overhead is reduced by nearly 40 percent.

Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is hindered by the significant resource requirements during inference. In this paper, we study two approaches for mitigating these challenges: employing a cache to store previous queries and learning a model multiplexer to choose from an ensemble of models for query processing. Theoretically, we provide an optimal algorithm for jointly optimizing both approaches to reduce the inference cost in both offline and online tabular settings. By combining a caching algorithm, namely Greedy Dual Size with Frequency (GDSF) or Least Expected Cost (LEC), with a model multiplexer, we achieve optimal rates in both offline and online settings. Empirically, simulations show that the combination of our caching and model multiplexing algorithms greatly improves over the baselines, with up to 50times improvement over the baseline when the ratio between the maximum cost and minimum cost is 100. Experiments on real datasets show a 4.3times improvement in FLOPs over the baseline when the ratio for FLOPs is 10, and a 1.8times improvement in latency when the ratio for average latency is 1.85.

This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. Our framework has three advantages. The first is accurate question answering. We designed a straightforward RAG scheme based on (1) a specific data processing workflow (2) dual-route sparse retrieval for coarse ranking (3) LLM Reranker for reranking (4) LLM answer generation and optimization. This approach achieved first place in the GLM4 track in the preliminary round and second place in the GLM4 track in the semifinals. The second is simple deployment. Our method primarily consists of BM25 retrieval and BGE-reranker reranking, requiring no fine-tuning of any models, occupying minimal VRAM, easy to deploy, and highly scalable; we provide a flexible code library with various search and generation strategies, facilitating custom process implementation. The last one is efficient inference. We designed an efficient inference acceleration scheme for the entire coarse ranking, reranking, and generation process that significantly reduces the inference latency of RAG while maintaining a good level of accuracy; each acceleration scheme can be plug-and-play into any component of the RAG process, consistently enhancing the efficiency of the RAG system. Our code and data are released at https://github.com/BUAADreamer/EasyRAG.

Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial, especially for long-output generation tasks based on the following two observations: (i) Excessive compression during the prefill phase, which requires specific full context impairs the comprehension of the reasoning task; (ii) Deviation of heavy hitters occurs in the reasoning tasks with long outputs. Therefore, SCOPE, a simple yet efficient framework that separately performs KV cache optimization during the prefill and decoding phases, is introduced. Specifically, the KV cache during the prefill phase is preserved to maintain the essential information, while a novel strategy based on sliding is proposed to select essential heavy hitters for the decoding phase. Memory usage and memory transfer are further optimized using adaptive and discontinuous strategies. Extensive experiments on LongGenBench show the effectiveness and generalization of SCOPE and its compatibility as a plug-in to other prefill-only KV compression methods.

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory footprint of the transient state, known as the key-value (KV) cache, which scales with the sequence length and batch size. In this paper, we present InfiniGen, a novel KV cache management framework tailored for long-text generation, which synergistically works with modern offloading-based inference systems. InfiniGen leverages the key insight that a few important tokens that are essential for computing the subsequent attention layer in the Transformer can be speculated by performing a minimal rehearsal with the inputs of the current layer and part of the query weight and key cache of the subsequent layer. This allows us to prefetch only the essential KV cache entries (without fetching them all), thereby mitigating the fetch overhead from the host memory in offloading-based LLM serving systems. Our evaluation on several representative LLMs shows that InfiniGen improves the overall performance of a modern offloading-based system by up to 3.00x compared to prior KV cache management methods while offering substantially better model accuracy.

In this paper, we introduce a multi-label lazy learning approach to deal with automatic semantic indexing in large document collections in the presence of complex and structured label vocabularies with high inter-label correlation. The proposed method is an evolution of the traditional k-Nearest Neighbors algorithm which uses a large autoencoder trained to map the large label space to a reduced size latent space and to regenerate the predicted labels from this latent space. We have evaluated our proposal in a large portion of the MEDLINE biomedical document collection which uses the Medical Subject Headings (MeSH) thesaurus as a controlled vocabulary. In our experiments we propose and evaluate several document representation approaches and different label autoencoder configurations.

Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, router performance engineering, policy conflict detection, low-latency embedding models, category-aware semantic caching, user-feedback-driven routing adaptation, hallucination detection, and hierarchical content-safety classification for privacy and jailbreak protection; (2) fleet optimization -- fleet provisioning and energy-efficiency analysis; (3) agentic and multimodal routing -- multimodal agent routing, tool selection, CUA security, and multi-turn context memory and safety; (4) governance and standards -- inference routing protocols and multi-provider API extensions. Each paper tackled a specific problem in LLM inference, but the problems are not independent; for example, fleet provisioning depends on the routing policy, which depends on the workload mix, shifting as organizations adopt agentic and multimodal workloads. This paper distills those results into the Workload-Router-Pool (WRP) architecture, a three-dimensional framework for LLM inference optimization. Workload characterizes what the fleet serves (chat vs. agent, single-turn vs. multi-turn, warm vs. cold, prefill-heavy vs. decode-heavy). Router determines how each request is dispatched (static semantic rules, online bandit adaptation, RL-based model selection, quality-aware cascading). Pool defines where inference runs (homogeneous vs. heterogeneous GPU, disaggregated prefill/decode, KV-cache topology). We map our prior work onto a 3x3 WRP interaction matrix, identify which cells we have covered and which remain open, and propose twenty-one concrete research directions at the intersections, each grounded in our prior measurements, tiered by maturity from engineering-ready to open research.

In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. Drawing on Cognitive Load Theory (CLT), we argue that this uninformative structure increases extraneous cognitive load, consuming finite working memory capacity that should be allocated to deep reasoning and attention allocation. To address this, we propose RePo, a novel mechanism that reduces extraneous load via context re-positioning. Unlike standard approaches, RePo utilizes a differentiable module, f_φ, to assign token positions that capture contextual dependencies, rather than replying on pre-defined integer range. By continually pre-training on the OLMo-2 1B backbone, we demonstrate that RePo significantly enhances performance on tasks involving noisy contexts, structured data, and longer context length, while maintaining competitive performance on general short-context tasks. Detailed analysis reveals that RePo successfully allocate higher attention to distant but relevant information, assign positions in dense and non-linear space, and capture the intrinsic structure of the input context. Our code is available at https://github.com/SakanaAI/repo.

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in concurrent serving scenarios. We present FastCache, a novel serving framework that effectively addresses these challenges through two key innovations: (1) a dynamic batching strategy that optimizes request scheduling across prefill, compression, and decode stages, and (2) an efficient KV-cache memory pool mechanism that eliminates memory fragmentation while maintaining high GPU utilization. Our comprehensive experiments on the GQA and MileBench datasets demonstrate that FastCache achieves up to 19.3times reduction in Time-To-First-Token (TTFT) and 12.1times improvement in throughput compared to state-of-the-art baselines. The system maintains stable performance under high-concurrency scenarios (up to 40 req/s) while reducing average memory consumption by 20\%. These results establish FastCache as an efficient solution for real-world LLM serving systems with KV-cache compression.

The complexity of large language model (LLM) serving workloads has substantially increased due to the integration with external tool invocations, such as ChatGPT plugins. In this paper, we identify a new opportunity for efficient LLM serving for requests that trigger tools: tool partial execution alongside LLM decoding. To this end, we design Conveyor, an efficient LLM serving system optimized for handling requests involving external tools. We introduce a novel interface for tool developers to expose partial execution opportunities to the LLM serving system and a request scheduler that facilitates partial tool execution. Our results demonstrate that tool partial execution can improve request completion latency by up to 38.8%.

Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-world studies reveal that over 70% of user requests to LLMs have semantically similar counterparts, suggesting the potential for knowledge transfer among requests. However, naively caching and reusing past responses leads to a big quality drop. In this paper, we introduce IC-Cache, a caching system that enables live LLM capability augmentation to improve serving efficiency: by leveraging historical request-response pairs from larger models as in-context examples, IC-Cache empowers small LLMs to imitate and even exceed the compositional abilities (e.g., reasoning) of their larger counterparts, enabling selective offloading of requests to reduce cost and latency. Achieving this live augmentation at scale introduces intricate trade-offs between response quality, latency, and system throughput. For a new request, IC-Cache efficiently selects similar, high-utility examples to prepend them to the new request's input. At scale, it adaptively routes requests across LLMs of varying capabilities, accounting for response quality and serving loads. IC-Cache employs a cost-aware cache replay mechanism that refines example quality offline to maximize online cache utility and efficiency. Evaluations on millions of realistic requests demonstrate that IC-Cache improves LLM serving throughput by 1.4-5.9x and reduces latency by 28-71% without hurting response quality.

Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires modifying model weights, creating stateful parameters that complicate concurrent serving. We propose Latent Context Compilation, a framework that fundamentally shifts context processing from adaptation to compilation. By utilizing a disposable LoRA module as a compiler, we distill long contexts into compact buffer tokens -- stateless, portable memory artifacts that are plug-and-play compatible with frozen base models. Crucially, we introduce a self-aligned optimization strategy that eliminates the need for synthetic context-relevant QA pairs. By regularizing context reconstruction task with context-agnostic random queries, we force compressed tokens to reside within the model's existing instruction-following manifold. Experiments with Llama-3.1-8B demonstrate that Latent Context Compilation preserves fine-grained details and reasoning capabilities where prior methods falter, effectively decoupling memory density from model parameters even at a 16x compression ratio.

Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However, existing LLM serving systems ignore dependencies between programs and calls, missing significant opportunities for optimization. Our analysis reveals that programs submitted to LLM serving engines experience long cumulative wait times, primarily due to head-of-line blocking at both the individual LLM request and the program. To address this, we introduce Autellix, an LLM serving system that treats programs as first-class citizens to minimize their end-to-end latencies. Autellix intercepts LLM calls submitted by programs, enriching schedulers with program-level context. We propose two scheduling algorithms-for single-threaded and distributed programs-that preempt and prioritize LLM calls based on their programs' previously completed calls. Our evaluation demonstrates that across diverse LLMs and agentic workloads, Autellix improves throughput of programs by 4-15x at the same latency compared to state-of-the-art systems, such as vLLM.

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality). Streaming context incrementally--overlapping retrieval with inference--can mitigate this latency, but doing so with concurrent requests introduces new challenges: requests contend for GPU compute and memory, and scheduling must adapt to dynamic context arrivals. We present Stream2LLM, a streaming-aware LLM serving system for concurrent prefill-decode disaggregated deployments. Stream2LLM introduces adaptive scheduling and preemption for two distinct retrieval patterns: append-mode (progressive context accumulation) and update-mode (iterative refinement with cache invalidation). It decouples scheduling decisions from resource acquisition, enabling flexible preemption strategies guided by hardware-specific cost models, and uses longest common prefix matching to minimize redundant computation when input changes dynamically. To evaluate Stream2LLM, we collect two large-scale, real-world streaming workloads based on web crawling and approximate nearest neighbor search. Our evaluation demonstrates that streaming architecture delivers up to 11x TTFT improvements, with cost-aware scheduling providing critical benefits under memory pressure, all while maintaining throughput parity with non-streaming baselines. Code: https://github.com/rajveerb/stream2llm/tree/mlsys_artifact

Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retrieval-augmented generation (RAG), which stores verbatim documents externally (as chunks) and retrieves only a relevant subset at inference time for an LLM to reason over. However, this results in inefficient usage of test-time compute (LLM repeatedly reasons over the same documents); moreover, chunk retrieval can inject irrelevant context that increases unsupported generation. We propose a human-like non-parametric continual learning framework, where the base model remains fixed, and learning occurs by integrating each new experience into an external semantic memory state that accumulates and consolidates itself continually. We present Panini, which realizes this by representing documents as Generative Semantic Workspaces (GSW) -- an entity- and event-aware network of question-answer (QA) pairs, sufficient for an LLM to reconstruct the experienced situations and mine latent knowledge via reasoning-grounded inference chains on the network. Given a query, Panini only traverses the continually-updated GSW (not the verbatim documents or chunks), and retrieves the most likely inference chains. Across six QA benchmarks, Panini achieves the highest average performance, 5%-7% higher than other competitive baselines, while using 2-30x fewer answer-context tokens, supports fully open-source pipelines, and reduces unsupported answers on curated unanswerable queries. The results show that efficient and accurate structuring of experiences at write time -- as achieved by the GSW framework -- yields both efficiency and reliability gains at read time. Code is available at https://github.com/roychowdhuryresearch/gsw-memory.

Industrial-scale user representation learning requires balancing robust universality with acute task-sensitivity. However, existing paradigms primarily yield static, task-agnostic embeddings that struggle to reconcile the divergent requirements of downstream scenarios within unified vector spaces. Furthermore, heterogeneous multi-source data introduces inherent noise and modality conflicts, degrading representation. We propose Query-as-Anchor, a framework shifting user modeling from static encoding to dynamic, query-aware synthesis. To empower Large Language Models (LLMs) with deep user understanding, we first construct UserU, an industrial-scale pre-training dataset that aligns multi-modal behavioral sequences with user understanding semantics, and our Q-Anchor Embedding architecture integrates hierarchical coarse-to-fine encoders into dual-tower LLMs via joint contrastive-autoregressive optimization for query-aware user representation. To bridge the gap between general pre-training and specialized business logic, we further introduce Cluster-based Soft Prompt Tuning to enforce discriminative latent structures, effectively aligning model attention with scenario-specific modalities. For deployment, anchoring queries at sequence termini enables KV-cache-accelerated inference with negligible incremental latency. Evaluations on 10 Alipay industrial benchmarks show consistent SOTA performance, strong scalability, and efficient deployment. Large-scale online A/B testing in Alipay's production system across two real-world scenarios further validates its practical effectiveness. Our code is prepared for public release and will be available at: https://github.com/JhCircle/Q-Anchor.

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each input sequence across multiple devices and necessitates communication to process the sequence. In essence, existing sequence parallelism methods assume homogeneous sequence lengths (i.e., all input sequences are equal in length) and therefore leverages a single, static scattering strategy for all input sequences. However, in reality, the sequence lengths in LLM training corpora exhibit substantial variability, often following a long-tail distribution, which leads to workload heterogeneity. In this paper, we show that employing a single, static strategy results in inefficiency and resource under-utilization, highlighting the need for adaptive approaches to handle the heterogeneous workloads across sequences. To address this, we propose a heterogeneity-adaptive sequence parallelism method. For each training step, our approach captures the variability in sequence lengths and assigns the optimal combination of scattering strategies based on workload characteristics. We model this problem as a linear programming optimization and design an efficient and effective solver to find the optimal solution. Furthermore, we implement our method in a high-performance system that supports adaptive parallelization in distributed LLM training. Experimental results demonstrate that our system outperforms state-of-the-art training frameworks by up to 1.98x.

Long-context language models exhibit impressive performance but remain challenging to deploy due to high GPU memory demands during inference. We propose Memory-efficient Offloaded Mini-sequence Inference (MOM), a method that partitions critical layers into smaller "mini-sequences" and integrates seamlessly with KV cache offloading. Experiments on various Llama, Qwen, and Mistral models demonstrate that MOM reduces peak memory usage by over 50\% on average. On Meta-Llama-3.2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU, while keeping outputs identical and not compromising accuracy. MOM also maintains highly competitive throughput due to minimal computational overhead and efficient last-layer processing. Compared to traditional chunked prefill methods, MOM achieves a 35\% greater context length extension. More importantly, our method drastically reduces prefill memory consumption, eliminating it as the longstanding dominant memory bottleneck during inference. This breakthrough fundamentally changes research priorities, redirecting future efforts from prefill-stage optimizations to improving decode-stage residual KV cache efficiency.

Large language models (LLMs) are increasingly used for complex tasks requiring multiple chained generation calls, advanced prompting techniques, control flow, and interaction with external environments. However, efficient systems for programming and executing these applications are lacking. To bridge this gap, we introduce SGLang, a Structured Generation Language for LLMs. SGLang is designed for the efficient programming of LLMs and incorporates primitives for common LLM programming patterns. We have implemented SGLang as a domain-specific language embedded in Python, and we developed an interpreter, a compiler, and a high-performance runtime for SGLang. These components work together to enable optimizations such as parallelism, batching, caching, sharing, and other compilation techniques. Additionally, we propose RadixAttention, a novel technique that maintains a Least Recently Used (LRU) cache of the Key-Value (KV) cache for all requests in a radix tree, enabling automatic KV cache reuse across multiple generation calls at runtime. SGLang simplifies the writing of LLM programs and boosts execution efficiency. Our experiments demonstrate that SGLang can speed up common LLM tasks by up to 5x, while reducing code complexity and enhancing control.

Many applications must provide low-latency LLM service to users or risk unacceptable user experience. However, over-provisioning resources to serve fluctuating request patterns is often prohibitively expensive. In this work, we present a best-effort serving system that employs deep reinforcement learning to adjust service quality based on the task distribution and system load. Our best-effort system can maintain availability with over 10x higher client request rates, serves above 96% of peak performance 4.1x more often, and serves above 98% of peak performance 2.3x more often than static serving on unpredictable workloads. Our learned router is robust to shifts in both the arrival and task distribution. Compared to static serving, learned best-effort serving allows for cost-efficient serving through increased hardware utility. Additionally, we argue that learned best-effort LLM serving is applicable in wide variety of settings and provides application developers great flexibility to meet their specific needs.

This paper presents MoE-Infinity, a cost-efficient mixture-of-expert (MoE) serving system that realizes activation-aware expert offloading. MoE-Infinity features sequence-level expert activation tracing, a new approach adept at identifying sparse activations and capturing the temporal locality of MoE inference. By analyzing these traces, MoE-Infinity performs novel activation-aware expert prefetching and caching, substantially reducing the latency overheads usually associated with offloading experts for improved cost performance. Extensive experiments in a cluster show that MoE-Infinity outperforms numerous existing systems and approaches, reducing latency by 4 - 20X and decreasing deployment costs by over 8X for various MoEs. MoE-Infinity's source code is publicly available at https://github.com/TorchMoE/MoE-Infinity

Retrieval-augmented generation (RAG) has gained traction as a powerful approach for enhancing language models by integrating external knowledge sources. However, RAG introduces challenges such as retrieval latency, potential errors in document selection, and increased system complexity. With the advent of large language models (LLMs) featuring significantly extended context windows, this paper proposes an alternative paradigm, cache-augmented generation (CAG) that bypasses real-time retrieval. Our method involves preloading all relevant resources, especially when the documents or knowledge for retrieval are of a limited and manageable size, into the LLM's extended context and caching its runtime parameters. During inference, the model utilizes these preloaded parameters to answer queries without additional retrieval steps. Comparative analyses reveal that CAG eliminates retrieval latency and minimizes retrieval errors while maintaining context relevance. Performance evaluations across multiple benchmarks highlight scenarios where long-context LLMs either outperform or complement traditional RAG pipelines. These findings suggest that, for certain applications, particularly those with a constrained knowledge base, CAG provide a streamlined and efficient alternative to RAG, achieving comparable or superior results with reduced complexity.

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL frameworks face challenges in complex dataflows and the corresponding resource idling and workload imbalance. Moreover, most existing frameworks are tightly coupled with LLM training or inference engines, making it difficult to support custom-designed engines. To address these challenges, we propose AsyncFlow, an asynchronous streaming RL framework for efficient post-training. Specifically, we introduce a distributed data storage and transfer module that provides a unified data management and fine-grained scheduling capability in a fully streamed manner. This architecture inherently facilitates automated pipeline overlapping among RL tasks and dynamic load balancing. Moreover, we propose a producer-consumer-based asynchronous workflow engineered to minimize computational idleness by strategically deferring parameter update process within staleness thresholds. Finally, the core capability of AsynFlow is architecturally decoupled from underlying training and inference engines and encapsulated by service-oriented user interfaces, offering a modular and customizable user experience. Extensive experiments demonstrate an average of 1.59 throughput improvement compared with state-of-the-art baseline. The presented architecture in this work provides actionable insights for next-generation RL training system designs.

In traditional RAG framework, the basic retrieval units are normally short. The common retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design forces the retriever to search over a large corpus to find the `needle' unit. In contrast, the readers only need to extract answers from the short retrieved units. Such an imbalanced `heavy' retriever and `light' reader design can lead to sub-optimal performance. In order to alleviate the imbalance, we propose a new framework LongRAG, consisting of a `long retriever' and a `long reader'. LongRAG processes the entire Wikipedia into 4K-token units, which is 30x longer than before. By increasing the unit size, we significantly reduce the total units from 22M to 700K. This significantly lowers the burden of retriever, which leads to a remarkable retrieval score: answer recall@1=71% on NQ (previously 52%) and answer recall@2=72% (previously 47%) on HotpotQA (full-wiki). Then we feed the top-k retrieved units (approx 30K tokens) to an existing long-context LLM to perform zero-shot answer extraction. Without requiring any training, LongRAG achieves an EM of 62.7% on NQ, which is the best known result. LongRAG also achieves 64.3% on HotpotQA (full-wiki), which is on par of the SoTA model. Our study offers insights into the future roadmap for combining RAG with long-context LLMs.

Retrieval-Augmented Language Modeling (RALM) by integrating large language models (LLM) with relevant documents from an external corpus is a proven method for enabling the LLM to generate information beyond the scope of its pre-training corpus. Previous work using utilizing retrieved content by simply prepending retrieved contents to the input poses a high runtime issue, which degrades the inference efficiency of the LLMs because they fail to use the Key-Value (KV) cache efficiently. In this paper, we propose FlashBack, a modular RALM designed to improve the inference efficiency of RALM with appending context pattern while maintaining decent performance after specific fine-tuning without heavily destruct the knowledge integrity of the LLM. FlashBack appends retrieved documents at the end of the context for efficiently utilizing the KV cache instead of prepending them. Our experiment shows that the inference speed of FlashBack is up to 4times faster than the prepending method on a 7B LLM (Llama 2). Via bypassing unnecessary re-computation, it demonstrates an advancement by achieving significantly faster inference speed, and this heightened efficiency will substantially reduce inferential cost. Our code will be publicly available.

The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing retrieval-based methods often compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning. In this paper, we propose LycheeCluster, a novel method for efficient KV cache management. LycheeCluster preserves local semantic coherence via boundary-aware chunking and constructs a recursive hierarchical index rooted in the triangle inequality. This design transforms cache retrieval from a linear scan into a theoretically bounded, logarithmic-time pruning process, while a lazy update strategy supports efficient streaming generation. Experiments demonstrate that LycheeCluster achieves up to a 3.6x end-to-end inference speedup with negligible degradation in model performance, outperforming state-of-the-art KV cache management methods (e.g., Quest, ClusterKV). We will release our code and kernels after publication.

In this paper, we point out that the objective of the retrieval algorithms is to align with the LLM, which is similar to the objective of knowledge distillation in LLMs. We analyze the similarity in information focus between the distilled language model(DLM) and the original LLM from the perspective of information theory, and thus propose a novel paradigm that leverages a DLM as the retrieval algorithm. Based on the insight, we present SpeContext, an algorithm and system co-design for long-context reasoning. (1) At the algorithm level, SpeContext proposes lightweight retrieval head based on the head-level attention weights of DLM, achieving > 90% parameters reduction by pruning the redundancy. (2) At the system level, SpeContext designs an asynchronous prefetch dataflow via the elastic loading strategy, effectively overlapping KV cache retrieval with the LLM computation. (3) At the compilation level, SpeContext constructs the theoretical memory model and implements an adaptive memory management system to achieve acceleration by maximizing GPU memory utilization. We deploy and evaluate SpeContext in two resourceconstrained environments, cloud and edge. Extensive experiments show that, compared with the Huggingface framework, SpeContext achieves up to 24.89x throughput improvement in cloud and 10.06x speedup in edge with negligible accuracy loss, pushing the Pareto frontier of accuracy and throughput.

Large language models (LLMs) are often augmented with tools to solve complex tasks. By generating code snippets and executing them through task-specific Application Programming Interfaces (APIs), they can offload certain functions to dedicated external modules, such as image encoding and performing calculations. However, most existing approaches to augment LLMs with tools are constrained by general-purpose APIs and lack the flexibility for tailoring them to specific tasks. In this work, we present CRAFT, a general tool creation and retrieval framework for LLMs. It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. For each task, we collect specific code solutions by prompting GPT-4 to solve the training examples. Following a validation step ensuring the correctness, these solutions are abstracted into code snippets to enhance reusability, and deduplicated for higher quality. At inference time, the language model retrieves snippets from the toolsets and then executes them or generates the output conditioning on the retrieved snippets. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning. Experiments on vision-language, tabular processing, and mathematical reasoning tasks show that our approach achieves substantial improvements compared to strong baselines. In addition, our in-depth analysis reveals that: (1) consistent performance improvement can be achieved by scaling up the number of tools and the capability of the backbone models; (2) each component of our approach contributes to the performance gains; (3) the created tools are well-structured and reliable with low complexity and atomicity. The code is available at https://github.com/lifan-yuan/CRAFT.

Large Language Models (LLMs) and Code-LLMs (CLLMs) have significantly improved code generation, but, they frequently face difficulties when dealing with challenging and complex problems. Retrieval-Augmented Generation (RAG) addresses this issue by retrieving and integrating external knowledge at the inference time. However, retrieval models often fail to find most relevant context, and generation models, with limited context capacity, can hallucinate when given irrelevant data. We present a novel framework that leverages a Programming Knowledge Graph (PKG) to semantically represent and retrieve code. This approach enables fine-grained code retrieval by focusing on the most relevant segments while reducing irrelevant context through a tree-pruning technique. PKG is coupled with a re-ranking mechanism to reduce even more hallucinations by selectively integrating non-RAG solutions. We propose two retrieval approaches-block-wise and function-wise-based on the PKG, optimizing context granularity. Evaluations on the HumanEval and MBPP benchmarks show our method improves pass@1 accuracy by up to 20%, and outperforms state-of-the-art models by up to 34% on MBPP. Our contributions include PKG-based retrieval, tree pruning to enhance retrieval precision, a re-ranking method for robust solution selection and a Fill-in-the-Middle (FIM) enhancer module for automatic code augmentation with relevant comments and docstrings.

We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.

Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an LLM to generate the query, then use a web search engine to retrieve contexts. Furthermore, to better align the query to the frozen modules, we propose a trainable scheme for our pipeline. A small language model is adopted as a trainable rewriter to cater to the black-box LLM reader. The rewriter is trained using the feedback of the LLM reader by reinforcement learning. Evaluation is conducted on downstream tasks, open-domain QA and multiple-choice QA. Experiments results show consistent performance improvement, indicating that our framework is proven effective and scalable, and brings a new framework for retrieval-augmented LLM.

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges, typically by offloading the complete KV cache to CPU and retrieving necessary tokens on demand during inference. However, these methods still suffer from unsatisfactory accuracy degradation and extra retrieval overhead. To address these limitations, this paper proposes A^2ATS, a novel retrieval-based KV cache reduction method. A^2ATS aims to obtain an accurate approximation of attention scores by applying the vector quantization technique to key states, thereby enabling efficient and precise retrieval of the top-K tokens. First, we propose Windowed Rotary Position Embedding, which decouples the positional dependency from query and key states after position embedding. Then, we propose query-aware vector quantization that optimizes the objective of attention score approximation directly. Finally, we design the heterogeneous inference architecture for KV cache offloading, enabling long context serving with larger batch sizes. Experimental results demonstrate that A^2ATS can achieve a lower performance degradation with similar or lower overhead compared to existing methods, thereby increasing long context serving throughput by up to 2.7 times.

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.

Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We introduce a data-driven computational model centred on stateful sessions: a persistent KV cache advanced incrementally as new data arrives, so prefill is moved off the critical path and query latency becomes O(|q|), independent of accumulated context size. Building on this, Flash Queries reclaim idle GPU cycles between data arrivals to pre-evaluate registered questions and return cached answers before the user asks, a pattern that is structurally impossible in stateless engines because they discard intermediate state between requests. A multi-tenant continuous-batching scheduler with cell-budget admission and prefix-aware grouped prefill lets dozens of stateful sessions coexist on a single GPU while preserving full quadratic self-attention. On streaming market-data benchmarks the reference implementation achieves up to 5.9x speedup over conventional inference engines (vLLM, SGLang, TensorRT-LLM, llama.cpp), holding query latency constant as accumulated context grows.

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory inference but often suffer from efficiency due to I/O bottlenecks. To achieve low-latency LLMs inference on resource-constrained devices, we introduce HeteGen, a novel approach that presents a principled framework for heterogeneous parallel computing using CPUs and GPUs. Based on this framework, HeteGen further employs heterogeneous parallel computing and asynchronous overlap for LLMs to mitigate I/O bottlenecks. Our experiments demonstrate a substantial improvement in inference speed, surpassing state-of-the-art methods by over 317% at most.

Increasing demand for Large Language Models (LLMs) services imposes substantial deployment and computation costs on providers. LLM routing offers a cost-efficient solution by directing queries to the optimal LLM based on model and query features. However, existing works primarily focus on offline scenarios and struggle to adapt to online settings with high query volume and constrained token budgets. In this work, we introduce the first training-free algorithm for online routing scenarios. Our algorithm leverages approximate nearest neighbor search to efficiently estimate query features and performs a one-time optimization over a small set of initial queries to learn a routing strategy that guides future routing. We provide theoretical guarantees demonstrating that our algorithm achieves a competitive ratio of 1 - o(1) under natural assumptions, which is further validated by extensive experiments across 3 benchmark datasets and 8 baselines, showing an average improvement of 3.55times in overall performance, 1.85times in cost efficiency, and nearly 4.25times in throughput. Our code is available at https://github.com/fzwark/PORT.

Modern language models increasingly adopt hybrid architectures that combine full attention with efficient attention modules, such as sliding-window attention (SWA) and recurrent sequence mixers. However, how these efficient modules shape model capabilities remains poorly understood. To address this gap, we conduct a systematic analysis across hybrid architectures from three perspectives: scaling behavior, mechanism analysis, and architecture design. First, from a scaling perspective, we find that efficient-attention design primarily affects how fast long-context capability emerges, while different hybrids eventually converge to comparable long-context performance under sufficient training. Second, mechanistically, we show that long-range retrieval is mainly carried by full attention, whereas efficient attention shapes its optimization trajectory. This explains a counter-intuitive phenomenon we call Large-Window Laziness: larger SWA windows can delay the formation of retrieval heads in full-attention layers. Third, guided by this mechanism, we show that applying NoPE to only the full-attention layers of a small-window SWA hybrid substantially improves long-context performance with negligible impact on short-context performance.

The performance of multi-turn, agentic LLM inference is increasingly dominated by KV-Cache storage I/O rather than computation. In prevalent disaggregated architectures, loading the massive KV-Cache from external storage creates a fundamental imbalance: storage NICs on prefill engines become bandwidth-saturated, while those on decoding engines remain idle. This asymmetry severely constrains overall system throughput. We present DualPath, an inference system that breaks this bottleneck by introducing dual-path KV-Cache loading. Beyond the traditional storage-to-prefill path, DualPath enables a novel storage-to-decode path, in which the KV-Cache is loaded into decoding engines and then efficiently transferred to prefill engines via RDMA over the compute network. DualPath combines this optimized data path -- which inherently avoids network congestion and avoids interference with latency-critical model execution communications -- with a global scheduler that dynamically balances load across prefill and decode engines. Our evaluation on three models with production agentic workloads demonstrates that DualPath improves offline inference throughput by up to 1.87times on our in-house inference system. It can also improve online serving throughput by an average factor of 1.96times without violating SLO.

Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear KV cache growth. Prior approaches mitigate this via post-hoc selection or eviction but overlook the root inefficiency: indiscriminate writing to memory. In this paper, we formalize KV cache management as a causal system of three primitives: KV Admission, Selection, and Eviction. We instantiate KV Admission via Write-Gated KV (WG-KV), a lightweight mechanism that learns to predict token utility before cache entry. By filtering out low-utility states early to maintain a compact global cache alongside a sliding local cache, WG-KV reduces memory usage by 46-68% and delivers 3.03-3.70x prefill and 1.85-2.56x decode speedups on Llama and Qwen models, while maintaining compatibility with FlashAttention and Paged-KV systems. These results demonstrate that learning what to write is a principled and practical recipe for efficient long-context inference. Code is available at https://github.com/EMCLab-Sinica/WG-KV.

Pipeline parallelism (PP) is widely used for training large language models (LLMs), yet its scalability is often constrained by high activation memory consumption as the number of in-flight microbatches grows with the degree of PP. In this paper, we focus on addressing this challenge by leveraging the under-explored memory offload strategy in PP. With empirical study, we discover that in the majority of standard configurations, at least half, and potentially all, of the activations can be offloaded with negligible overhead. In the cases where full overload is not possible, we introduce a novel selective offload strategy that decreases peak activation memory in a better-than-linear manner. Furthermore, we integrate memory offload with other techniques to jointly consider overall throughput and memory limitation. Our experiments proves that the per-device activation memory effectively reduces with the total number of stages, making PP a stronger alternative than TP, offering up to a 19\% acceleration with even lower memory consumption. The implementation is open-sourced at https://github.com/sail-sg/zero-bubble-pipeline-parallelism{this url}.

Sparse Mixture of Experts (MoE) models, while outperforming dense Large Language Models (LLMs) in terms of performance, face significant deployment challenges during inference due to their high memory demands. Existing offloading techniques, which involve swapping activated and idle experts between the GPU and CPU, often suffer from rigid expert caching mechanisms. These mechanisms fail to adapt to dynamic routing, leading to inefficient cache utilization, or incur prohibitive costs for prediction training. To tackle these inference-specific challenges, we introduce ExpertFlow, a comprehensive system specifically designed to enhance inference efficiency by accommodating flexible routing and enabling efficient expert scheduling between CPU and GPU. This reduces overhead and boosts system performance. Central to our approach is a predictive routing path-based offloading mechanism that utilizes a lightweight predictor to accurately forecast routing paths before computation begins. This proactive strategy allows for real-time error correction in expert caching, significantly increasing cache hit ratios and reducing the frequency of expert transfers, thereby minimizing I/O overhead. Additionally, we implement a dynamic token scheduling strategy that optimizes MoE inference by rearranging input tokens across different batches. This method not only reduces the number of activated experts per batch but also improves computational efficiency. Our extensive experiments demonstrate that ExpertFlow achieves up to 93.72\% GPU memory savings and enhances inference speed by 2 to 10 times compared to baseline methods, highlighting its effectiveness and utility as a robust solution for resource-constrained inference scenarios.

As large language models (LLMs) take on more complex tasks, their inputs incorporate longer contexts to respond to questions that require domain knowledge or user-specific conversational histories. Yet, using long contexts poses a challenge for responsive LLM systems, as nothing can be generated until all the contexts are fetched to and processed by the LLM. Existing systems optimize only the computation delay in context processing (e.g., by caching intermediate key-value features of the text context) but often cause longer network delays in context fetching (e.g., key-value features consume orders of magnitude larger bandwidth than the text context). This paper presents CacheGen to minimize the delays in fetching and processing contexts for LLMs. CacheGen reduces the bandwidth needed for transmitting long contexts' key-value (KV) features through a novel encoder that compresses KV features into more compact bitstream representations. The encoder combines adaptive quantization with a tailored arithmetic coder, taking advantage of the KV features' distributional properties, such as locality across tokens. Furthermore, CacheGen minimizes the total delay in fetching and processing a context by using a controller that determines when to load the context as compressed KV features or raw text and picks the appropriate compression level if loaded as KV features. We test CacheGen on three models of various sizes and three datasets of different context lengths. Compared to recent methods that handle long contexts, CacheGen reduces bandwidth usage by 3.7-4.3x and the total delay in fetching and processing contexts by 2.7-3x while maintaining similar LLM performance on various tasks as loading the text contexts.

Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion. However, the invariable use of retrieval in existing methods exposes issues in both efficiency and robustness, with a large proportion of the retrieved contexts proving unhelpful or harmful to code language models (code LMs). In this paper, we propose a selective RAG framework to avoid retrieval when unnecessary. To power this framework, we design a self-supervised learning approach to enable a code LM to accurately self-evaluate whether retrieval can improve its output quality and robustly leverage the potentially noisy retrieved contexts. Using this LM as both the selective RAG policy and the generation model, our framework achieves state-of-the-art repository-level code completion performance on diverse benchmarks including RepoEval, CrossCodeEval, and CrossCodeLongEval, a new long-form code completion benchmark. Meanwhile, our analyses show that selectively retrieving brings as much as 70% inference speedup in the online serving setting without harming the performance. We further demonstrate that our framework is able to accommodate different generation models, retrievers, and programming languages. These advancements position our framework as an important step towards more accurate and efficient repository-level code completion.

The rapid growth of Large Language Models (LLMs) has been a driving force in transforming various domains, reshaping the artificial general intelligence landscape. However, the increasing computational and memory demands of these models present substantial challenges, hindering both academic research and practical applications. To address these issues, a wide array of methods, including both algorithmic and hardware solutions, have been developed to enhance the efficiency of LLMs. This survey delivers a comprehensive review of algorithmic advancements aimed at improving LLM efficiency. Unlike other surveys that typically focus on specific areas such as training or model compression, this paper examines the multi-faceted dimensions of efficiency essential for the end-to-end algorithmic development of LLMs. Specifically, it covers various topics related to efficiency, including scaling laws, data utilization, architectural innovations, training and tuning strategies, and inference techniques. This paper aims to serve as a valuable resource for researchers and practitioners, laying the groundwork for future innovations in this critical research area. Our repository of relevant references is maintained at url{https://github.com/tding1/Efficient-LLM-Survey}.

LLM agents increasingly rely on retrieval buffers to store and reuse past experience, yet the cache management policies governing these buffers remain largely ad-hoc. We formalize this as an online semantic cache replacement problem with switching costs, where items are matched by embedding similarity and hit quality is continuous rather than binary. Through experiments on two datasets from MemoryBench-Full (LoCoMo, DialSim) with 8 replacement policies, we reveal a surprising finding: classic heuristics (LRU, LFU) consistently underperform the naive FIFO baseline on semantic workloads, due to the absence of temporal locality and frequency concentration. We propose SOLAR, a learning-augmented framework that derives modification timing from regret accumulation (achieving sim17\% modification rate) and content selection from Bayesian online learning over implicit retrieval feedback. We prove SOLAR achieves a constant competitive ratio leq 3, independent of cache size and horizon (vs.\ Ω(K) for FIFO), and eviction regret O(KTlog T), matching the Ω(KT) lower bound up to logarithmic factors. Experiments demonstrate 5--75\% relative improvement over FIFO at tight cache sizes, with a clearly characterized phase transition at the working set boundary. Synthetic experiments with 5000-item pools further reveal an inverted-U relationship between pool size and retrieval quality, justifying capacity constraints as a retrieval noise phenomenon rather than a storage limitation.

The rise of large language models (LLMs) has enabled LLM-based applications (a.k.a. AI agents or co-pilots), a new software paradigm that combines the strength of LLM and conventional software. Diverse LLM applications from different tenants could design complex workflows using multiple LLM requests to accomplish one task. However, they have to use the over-simplified request-level API provided by today's public LLM services, losing essential application-level information. Public LLM services have to blindly optimize individual LLM requests, leading to sub-optimal end-to-end performance of LLM applications. This paper introduces Parrot, an LLM service system that focuses on the end-to-end experience of LLM-based applications. Parrot proposes Semantic Variable, a unified abstraction to expose application-level knowledge to public LLM services. A Semantic Variable annotates an input/output variable in the prompt of a request, and creates the data pipeline when connecting multiple LLM requests, providing a natural way to program LLM applications. Exposing Semantic Variables to the public LLM service allows it to perform conventional data flow analysis to uncover the correlation across multiple LLM requests. This correlation opens a brand-new optimization space for the end-to-end performance of LLM-based applications. Extensive evaluations demonstrate that Parrot can achieve up to an order-of-magnitude improvement for popular and practical use cases of LLM applications.

Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient plug-and-play refiner that leverages the inherent structural characteristics of long documents. LongRefiner employs dual-level query analysis, hierarchical document structuring, and adaptive refinement through multi-task learning on a single foundation model. Experiments on seven QA datasets demonstrate that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to the best baseline. Further analysis validates that LongRefiner is scalable, efficient, and effective, providing practical insights for real-world long-text RAG applications. Our code is available at https://github.com/ignorejjj/LongRefiner.

Tool-augmented large language models have advanced from single-turn question answering to deep research workflows that iteratively plan queries, invoke external tools, and synthesize information to address complex information needs. Evaluating such workflows presents a fundamental challenge: reliance on live APIs introduces non-determinism, as tool invocations may yield different results across runs due to temporal drift, rate limiting, and evolving backend states. This variance undermines reproducibility and invalidates cross-system comparisons. We present ScholarGym, a simulation environment for reproducible evaluation of deep research workflows on academic literature. The environment decouples workflow components into query planning, tool invocation, and relevance assessment, enabling fine-grained analysis of each stage under controlled conditions. Built on a static corpus of 570K papers with deterministic retrieval, ScholarGym provides 2,536 queries with expert-annotated ground truth. Experiments across diverse backbone models reveal how reasoning capabilities, planning strategies, and selection mechanisms interact over iterative refinement.

The reasoning large language model (RLLM) has been proven competitive in solving complex reasoning tasks such as mathematics, coding, compared to general LLM. However, the serving performance and behavior of RLLM remains unexplored, which may undermine the deployment and utilization of RLLM in real-world scenario. To close this gap, in this paper, we conduct a comprehensive study of RLLM service. We first perform a pilot study on comparing the serving performance between RLLM and traditional LLM and reveal that there are several distinct differences regarding serving behavior: (1) significant memory usage and fluctuations; (2) straggler requests; (3) adaptive running time; (4) domain preference. Then we further investigate whether existing inference optimization techniques are valid for RLLM. Our main takeaways are that model quantization methods and speculative decoding can improve service system efficiency with small compromise to RLLM accuracy, while prefix caching, KV cache quantization may even degrade accuracy or serving performance for small RLLM. Lastly, we conduct evaluation under real world workload modeled by Gamma distribution to verify our findings. Empirical results of real world workload evaluation across different dataset are aligned with our main findings regarding RLLM serving. We hope our work can provide the research community and industry with insights to advance RLLM inference serving.

Coding agents are a fast-growing LLM application, executing as long-running closed-loop sessions in which LLM generations alternate with external tool calls. Yet, unlike chat workloads, their serving behavior has not been studied extensively. We address this gap by collecting a dataset of real-world coding assistant traces. Our analysis shows that coding agent sessions repeatedly reuse large prefixes and create sustained KVCache pressure that conventional LLM serving policies handle poorly. Based on our analysis, we present CacheWise, a KVCache management layer that improves KVCache reuse for coding agent workloads. CacheWise combines prefix-aware scheduling with reuse-aware eviction guided by lightweight predictions from tool call metadata. Implemented in vLLM and evaluated on the collected traces, CacheWise reduces KVCache evictions by up to 2-2.6x and improves total agent session completion time by up to 3.5x.

KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent workloads. Although many KV-cache compression methods improve offline accuracy or compression ratio, they often violate practical serving constraints such as paged memory layouts, regular memory access, and fused attention execution, limiting their effectiveness in deployment. In this work, we identify the minimal set of 4-bit KV-cache quantization methods that remain viable under these constraints. Our central finding is that a simple design--token-wise INT4 quantization with block-diagonal Hadamard rotation--consistently achieves the best accuracy-efficiency trade-off. Across multiple models and benchmarks, this approach recovers nearly all of the accuracy lost by naive INT4, while more complex methods such as vector quantization and Hessian-aware quantization provide only marginal additional gains once serving compatibility is taken into account. To make this practical, we implement a fused rotation-quantization kernel that integrates directly into paged KV-cache layouts and introduces zero measurable end-to-end overhead, matching plain INT4 throughput across concurrency levels. Our results show that effective KV-cache compression is fundamentally a systems co-design problem: under real serving constraints, lightweight block-diagonal Hadamard rotation is a viable method that delivers near-lossless accuracy without sacrificing serving efficiency.

Engineering efficient implementations of compact and succinct structures is a time-consuming and challenging task, since there is no standard library of easy-to- use, highly optimized, and composable components. One consequence is that measuring the practical impact of new theoretical proposals is a difficult task, since older base- line implementations may not rely on the same basic components, and reimplementing from scratch can be very time-consuming. In this paper we present a framework for experimentation with succinct data structures, providing a large set of configurable components, together with tests, benchmarks, and tools to analyze resource requirements. We demonstrate the functionality of the framework by recomposing succinct solutions for document retrieval.

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}.

Many applications need up-to-date copies of collections of changing Web resources. Such synchronization is currently achieved using ad-hoc or proprietary solutions. We propose ResourceSync, a general Web resource synchronization protocol that leverages XML Sitemaps. It provides a set of capabilities that can be combined in a modular manner to meet local or community requirements. We report on work to implement this protocol for arXiv.org and also provide an experimental prototype for the English Wikipedia as well as a client API.

Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whose memory footprints scale linearly with sequence length. We introduce OOMB, a highly memory-efficient training system that directly confronts this barrier. Our approach employs a chunk-recurrent training framework with on-the-fly activation recomputation, which maintains a constant activation memory footprint (O(1)) and shifts the primary bottleneck to the growing KV cache. To manage the KV cache, OOMB integrates a suite of synergistic optimizations: a paged memory manager for both the KV cache and its gradients to eliminate fragmentation, asynchronous CPU offloading to hide data transfer latency, and page-level sparse attention to reduce both computational complexity and communication overhead. The synergy of these techniques yields exceptional efficiency. Our empirical results show that for every additional 10K tokens of context, the end-to-end training memory overhead increases by a mere 10MB for Qwen2.5-7B. This allows training Qwen2.5-7B with a 4M-token context on a single H200 GPU, a feat that would otherwise require a large cluster using context parallelism. This work represents a substantial advance in resource efficiency for long-context LLM training. The source code is available at https://github.com/wenhaoli-xmu/OOMB.

The scale of biological datasets now routinely exceeds system memory, making data access rather than model computation the primary bottleneck in training machine-learning models. This bottleneck is particularly acute in biology, where widely used community data formats must support heterogeneous metadata, sparse and dense assays, and downstream analysis within established computational ecosystems. Here we present annbatch, a mini-batch loader native to anndata that enables out-of-core training directly on disk-backed datasets. Across single-cell transcriptomics, microscopy and whole-genome sequencing benchmarks, annbatch increases loading throughput by up to an order of magnitude and shortens training from days to hours, while remaining fully compatible with the scverse ecosystem. Annbatch establishes a practical data-loading infrastructure for scalable biological AI, allowing increasingly large and diverse datasets to be used without abandoning standard biological data formats. Github: https://github.com/scverse/annbatch

Long-context LLMs have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challenges, optimizations for long-context inference have been developed, centered around the KV cache. However, existing benchmarks often evaluate in single-request, neglecting the full lifecycle of the KV cache in real-world use. This oversight is particularly critical, as KV cache reuse has become widely adopted in LLMs inference frameworks, such as vLLM and SGLang, as well as by LLM providers, including OpenAI, Microsoft, Google, and Anthropic. To address this gap, we introduce SCBench(SharedContextBench), a comprehensive benchmark for evaluating long-context methods from a KV cachecentric perspective: 1) KV cache generation, 2) KV cache compression, 3) KV cache retrieval, 4) KV cache loading. Specifically, SCBench uses test examples with shared context, ranging 12 tasks with two shared context modes, covering four categories of long-context capabilities: string retrieval, semantic retrieval, global information, and multi-task. With it, we provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs, Mamba-Attention hybrids, and efficient methods such as sparse attention, KV cache dropping, quantization, retrieval, loading, and prompt compression. The evaluation is conducted on 8 long-context LLMs. Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n^2) pre-filling computation perform robustly. Dynamic sparsity yields more expressive KV caches than static patterns, and layer-level sparsity in hybrid architectures reduces memory usage with strong performance. Additionally, we identify attention distribution shift issues in long-generation scenarios. https://aka.ms/SCBench.

Serverless computing has emerged as a compelling new paradigm of cloud computing models in recent years. It promises the user services at large scale and low cost while eliminating the need for infrastructure management. On cloud provider side, flexible resource management is required to meet fluctuating demand. It can be enabled through automated provisioning and deprovisioning of resources. A common approach among both commercial and open source serverless computing platforms is workload-based auto-scaling, where a designated algorithm scales instances according to the number of incoming requests. In the recently evolving serverless framework Knative a request-based policy is proposed, where the algorithm scales resources by a configured maximum number of requests that can be processed in parallel per instance, the so-called concurrency. As we show in a baseline experiment, this predefined concurrency level can strongly influence the performance of a serverless application. However, identifying the concurrency configuration that yields the highest possible quality of service is a challenging task due to various factors, e.g. varying workload and complex infrastructure characteristics, influencing throughput and latency. While there has been considerable research into intelligent techniques for optimizing auto-scaling for virtual machine provisioning, this topic has not yet been discussed in the area of serverless computing. For this reason, we investigate the applicability of a reinforcement learning approach, which has been proven on dynamic virtual machine provisioning, to request-based auto-scaling in a serverless framework. Our results show that within a limited number of iterations our proposed model learns an effective scaling policy per workload, improving the performance compared to the default auto-scaling configuration.

Paper search is an important activity for researchers, typically involving using a query with description of a topic to find relevant papers. As research deepens, paper search requirements may become more flexible, sometimes involving specific details such as module configuration rather than being limited to coarse-grained topics. However, previous paper search systems are unable to meet these flexible-grained requirements, as these systems mainly collect paper abstracts to construct index of corpus, which lack detailed information to support retrieval by finer-grained queries. In this work, we propose PaperRegister, consisted of offline hierarchical indexing and online adaptive retrieval, transforming traditional abstract-based index into hierarchical index tree for paper search, thereby supporting queries at flexible granularity. Experiments on paper search tasks across a range of granularity demonstrate that PaperRegister achieves the state-of-the-art performance, and particularly excels in fine-grained scenarios, highlighting the good potential as an effective solution for flexible-grained paper search in real-world applications. Code for this work is in https://github.com/Li-Z-Q/PaperRegister.

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization and throughput at the cost of increased latency per token. In contrast, disaggregated serving decouples compute-bound prefill and bandwidth-bound decode phases to optimize for service level objectives (SLOs) at the cost of resource under-utilization and KV-cache transfer overheads. To address the limitations of these techniques, we propose RAPID-Serve: a technique to concurrently execute prefill and decode on the same GPU(s) to meet latency SLOs while maintaining high throughput and efficient resource utilization. Furthermore, we propose Adaptive Resource Management for runtime compute resource allocation, optionally leveraging CU masking (a fine-grained Compute Unit partitioning feature on AMD InstinctTM GPUs). RAPID-Serve provides up to 4.1x (average 1.7x) unconstrained throughput improvement and 32x and higher (average 4.9x) throughput improvement under SLO constraints, showing it as an effective strategy compared to the state-of-the-art approaches, particularly in resource-constrained environments.

To support reliable long-term interaction in complex environments, LLM agents require memory systems that efficiently manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high token costs. To address this challenge, we introduce SimpleMem, an efficient memory framework based on semantic lossless compression. We propose a three-stage pipeline designed to maximize information density and token utilization: (1) Semantic Structured Compression, which applies entropy-aware filtering to distill unstructured interactions into compact, multi-view indexed memory units; (2) Recursive Memory Consolidation, an asynchronous process that integrates related units into higher-level abstract representations to reduce redundancy; and (3) Adaptive Query-Aware Retrieval, which dynamically adjusts retrieval scope based on query complexity to construct precise context efficiently. Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost, achieving an average F1 improvement of 26.4% while reducing inference-time token consumption by up to 30-fold, demonstrating a superior balance between performance and efficiency. Code is available at https://github.com/aiming-lab/SimpleMem.

We present CIFLEX (Contextual Instruction Flow for Sub-task Execution), which is a novel execution system for efficient sub-task handling in multi-turn interactions with a single on-device large language model (LLM). As LLMs become increasingly capable, a single model is expected to handle diverse sub-tasks that more effectively and comprehensively support answering user requests. Naive approach reprocesses the entire conversation context when switching between main and sub-tasks (e.g., query rewriting, summarization), incurring significant computational overhead. CIFLEX mitigates this overhead by reusing the key-value (KV) cache from the main task and injecting only task-specific instructions into isolated side paths. After sub-task execution, the model rolls back to the main path via cached context, thereby avoiding redundant prefill computation. To support sub-task selection, we also develop a hierarchical classification strategy tailored for small-scale models, decomposing multi-choice decisions into binary ones. Experiments show that CIFLEX significantly reduces computational costs without degrading task performance, enabling scalable and efficient multi-task dialogue on-device.

The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI's ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges in the high consumption of computational, memory, energy, and financial resources, especially in environments with limited resource capabilities. This survey aims to systematically address these challenges by reviewing a broad spectrum of techniques designed to enhance the resource efficiency of LLMs. We categorize methods based on their optimization focus: computational, memory, energy, financial, and network resources and their applicability across various stages of an LLM's lifecycle, including architecture design, pretraining, finetuning, and system design. Additionally, the survey introduces a nuanced categorization of resource efficiency techniques by their specific resource types, which uncovers the intricate relationships and mappings between various resources and corresponding optimization techniques. A standardized set of evaluation metrics and datasets is also presented to facilitate consistent and fair comparisons across different models and techniques. By offering a comprehensive overview of the current sota and identifying open research avenues, this survey serves as a foundational reference for researchers and practitioners, aiding them in developing more sustainable and efficient LLMs in a rapidly evolving landscape.

Efficient use of GPU memory is essential for high throughput LLM inference. Prior systems reserved memory for the KV-cache ahead-of-time, resulting in wasted capacity due to internal fragmentation. Inspired by OS-based virtual memory systems, vLLM proposed PagedAttention to enable dynamic memory allocation for KV-cache. This approach eliminates fragmentation, enabling high-throughput LLM serving with larger batch sizes. However, to be able to allocate physical memory dynamically, PagedAttention changes the layout of KV-cache from contiguous virtual memory to non-contiguous virtual memory. This change requires attention kernels to be rewritten to support paging, and serving framework to implement a memory manager. Thus, the PagedAttention model leads to software complexity, portability issues, redundancy and inefficiency. In this paper, we propose vAttention for dynamic KV-cache memory management. In contrast to PagedAttention, vAttention retains KV-cache in contiguous virtual memory and leverages low-level system support for demand paging, that already exists, to enable on-demand physical memory allocation. Thus, vAttention unburdens the attention kernel developer from having to explicitly support paging and avoids re-implementation of memory management in the serving framework. We show that vAttention enables seamless dynamic memory management for unchanged implementations of various attention kernels. vAttention also generates tokens up to 1.97x faster than vLLM, while processing input prompts up to 3.92x and 1.45x faster than the PagedAttention variants of FlashAttention and FlashInfer.

Large Language Models (LLM)-based systems, i.e. interconnected elements that include an LLM as a central component (e.g., conversational agents), are typically monolithic static architectures that rely on a single LLM for all user queries. However, they often require different preprocessing strategies, levels of reasoning, or knowledge. Generalist LLMs (i.e. GPT-4), trained on very large multi-topic corpora, can perform well in a variety of tasks. However, they require significant financial, energy, and hardware resources that may not be justified for basic tasks. This implies potentially investing in unnecessary costs for a given query. To overcome this problem, a routing mechanism routes user queries to the most suitable components, such as smaller LLMs or experts in specific topics. This approach may improve response quality while minimising costs. Routing can be expanded to other components of the conversational agent architecture, such as the selection of optimal embedding strategies. This paper explores key considerations for integrating routing into LLM-based systems, focusing on resource management, cost definition, and strategy selection. Our main contributions include a formalisation of the problem, a novel taxonomy of existing approaches emphasising relevance and resource efficiency, and a comparative analysis of these strategies in relation to industry practices. Finally, we identify critical challenges and directions for future research.

Practical large language model (LLM) services may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across numerous requests. However, the long system prompt causes throughput/latency bottlenecks as the cost of generating the next token grows w.r.t. the sequence length. This paper aims to improve the efficiency of LLM services that involve long system prompts. Our key observation is that handling these system prompts requires heavily redundant memory accesses in existing causal attention computation algorithms. Specifically, for batched requests, the cached hidden states (i.e., key-value pairs) of system prompts are transferred from off-chip DRAM to on-chip SRAM multiple times, each corresponding to an individual request. To eliminate such a redundancy, we propose RelayAttention, an attention algorithm that allows reading these hidden states from DRAM exactly once for a batch of input tokens. RelayAttention is a free lunch: it maintains the generation quality while requiring no model retraining, as it is based on a mathematical reformulation of causal attention.

Recent advancements in LLM-based information-seeking agents have achieved record-breaking performance on established benchmarks. However, these agents remain heavily reliant on search-engine-indexed knowledge, leaving a critical blind spot: Unindexed Information Seeking (UIS). This paper identifies and explores the UIS problem, where vital information is not captured by search engine crawlers, such as overlooked content, dynamic webpages, and embedded files. Despite its significance, UIS remains an underexplored challenge. To address this gap, we introduce UIS-QA, the first dedicated UIS benchmark, comprising 110 expert-annotated QA pairs. Notably, even state-of-the-art agents experience a drastic performance drop on UIS-QA (e.g., from 70.90 on GAIA and 46.70 on BrowseComp-zh to 24.55 on UIS-QA), underscoring the severity of the problem. To mitigate this, we propose UIS-Digger, a novel multi-agent framework that incorporates dual-mode browsing and enables simultaneous webpage searching and file parsing. With a relatively small sim30B-parameter backbone LLM optimized using SFT and RFT training strategies, UIS-Digger sets a strong baseline at 27.27\%, outperforming systems integrating sophisticated LLMs such as O3 and GPT-4.1. This demonstrates the importance of proactive interaction with unindexed sources for effective and comprehensive information-seeking. Our work not only uncovers a fundamental limitation in current agent evaluation paradigms but also provides the first toolkit for advancing UIS research, defining a new and promising direction for robust information-seeking systems.

Large language model (LLM) agents often struggle in long-context interactions. As the agent accumulates more interaction history, context management approaches such as sliding window and prompt compression may omit earlier structured information that later steps rely on. Recent retrieval-based memory systems surface relevant content but still overlook the causal and logical structure needed for multi-step reasoning. We introduce ContextWeaver, a selective and dependency-structured memory framework that organizes an agent's interaction trace into a graph of reasoning steps and selects the relevant context for future actions. Unlike prior context management approaches, ContextWeaver supports: (1) dependency-based construction and traversal that link each step to the earlier steps it relies on; (2) compact dependency summarization that condenses root-to-step reasoning paths into reusable units; and (3) a lightweight validation layer that incorporates execution feedback. On the SWE-Bench Verified and Lite benchmarks, ContextWeaver improves performance over a sliding-window baseline in pass@1, while reducing reasoning steps and token usage. Our observations suggest that modeling logical dependencies provides a stable and scalable memory mechanism for LLM agents that use tools.

Serving systems for Large Language Models (LLMs) are often optimized to improve quality of service (QoS) and throughput. However, due to the lack of open-source LLM serving workloads, these systems are frequently evaluated under unrealistic workload assumptions. Consequently, performance may degrade when systems are deployed in real-world scenarios. This work presents BurstGPT, an LLM serving workload with 10.31 million traces from regional Azure OpenAI GPT services over 213 days. BurstGPT captures LLM serving characteristics from user, model and system perspectives: (1) User request concurrency: burstiness variations of requests in Azure OpenAI GPT services, revealing diversified concurrency patterns in different services and model types. (2) User conversation patterns: counts and intervals within conversations for service optimizations. (3) Model response lengths: auto-regressive serving processes of GPT models, showing statistical relations between requests and their responses. (4) System response failures: failures of conversation and API services, showing intensive resource needs and limited availability of LLM services in Azure. The details of the characteristics can serve multiple purposes in LLM serving optimizations, such as system evaluation and trace provisioning. In our demo evaluation with BurstGPT, frequent variations in BurstGPT reveal declines in efficiency, stability, or reliability in realistic LLM serving. We identify that the generalization of KV cache management, scheduling and disaggregation optimizations can be improved under realistic workload evaluations. BurstGPT is publicly available now at https://github.com/HPMLL/BurstGPT and is widely used to develop prototypes of LLM serving frameworks in the industry.

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token importance. We show that Compactor can achieve the same performance as competing methods while retaining 20% fewer tokens in both synthetic and real-world context tasks, while being more task-robust. We further introduce a procedure for context-calibrated compression: inferring the maximum compression a given context supports before significant performance loss. Using context-calibrated compression, we show that Compactor achieves full KV performance on Longbench while reducing the KV memory burden by 68%, on average. To demonstrate the efficacy and generalizability of our approach, we apply Compactor to 27 synthetic and real-world tasks from RULER and Longbench, with models from both the Qwen 2.5 and Llama 3.1 families. Finally, we release compactor-vllm, an inference engine and suite of optimized Triton kernels designed to efficiently support the sparse, non-contiguous memory access patterns inherent to compressed KV caches. This work demonstrates that Compactor offers a practical, high-performance solution for alleviating the memory bottleneck in modern LLM deployment.

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve general LLM but fail with Low-Rank Adaptation (LoRA) inference due to three key limitations: 1) massive parameter redundancy among functions where 99% of weights are unnecessarily duplicated, 2) costly artifact loading latency beyond LLM loading, and 3) magnified resource contention when serving multiple LoRA LLMs. These inefficiencies lead to massive GPU wastage, increased Time-To-First-Token (TTFT), and high monetary costs. We propose ServerlessLoRA, a novel serverless inference system designed for faster and cheaper LoRA LLM serving. ServerlessLoRA enables secure backbone LLM sharing across isolated LoRA functions to reduce redundancy. We design a pre-loading method that pre-loads comprehensive LoRA artifacts to minimize cold-start latency. Furthermore, ServerlessLoRA employs contention aware batching and offloading to mitigate GPU resource conflicts during bursty workloads. Experiment on industrial workloads demonstrates that ServerlessLoRA reduces TTFT by up to 86% and cuts monetary costs by up to 89% compared to state-of-the-art LLM inference solutions.

Large Language Models (LLMs)-based hybrid retrieval uses LLMs to encode queries and documents into low-dimensional dense or high-dimensional sparse vectors. It retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query encoder. Although LLMs significantly enhance retrieval capabilities, serving deeply parameterized LLMs slows down query inference throughput and increases demands for online deployment resources. In this paper, we propose LightRetriever, a novel LLM-based hybrid retriever with extremely lightweight query encoders. Our method retains a full-sized LLM for document encoding, but reduces the workload of query encoding to no more than an embedding lookup. Compared to serving a full-sized LLM on an H800 GPU, our approach achieves over a 1000x speedup for query inference with GPU acceleration, and even a 20x speedup without GPU. Experiments on large-scale retrieval benchmarks demonstrate that our method generalizes well across diverse retrieval tasks, retaining an average of 95% full-sized performance.

Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to address diverse real-world challenges. Assessing the capability of LLMs to utilise tools necessitates large-scale and stable benchmarks. However, previous works relied on either hand-crafted online tools with limited scale, or large-scale real online APIs suffering from instability of API status. To address this problem, we introduce StableToolBench, a benchmark evolving from ToolBench, proposing a virtual API server and stable evaluation system. The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status. Meanwhile, the stable evaluation system designs solvable pass and win rates using GPT-4 as the automatic evaluator to eliminate the randomness during evaluation. Experimental results demonstrate the stability of StableToolBench, and further discuss the effectiveness of API simulators, the caching system, and the evaluator system.

Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs). There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve). However, current dynamic RAG methods fall short in both aspects. Firstly, the strategies for deciding when to retrieve often rely on static rules. Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM's most recent sentence or the last few tokens, while the LLM's real-time information needs may span across the entire context. To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the real-time Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method. We have open-sourced all the code, data, and models in GitHub: https://github.com/oneal2000/DRAGIN/tree/main

LLMs are known to store vast amounts of knowledge in their parametric memory. However, learning and recalling facts from this memory is known to be unreliable, depending largely on the prevalence of particular facts in the training data and other factors which are poorly understood. Practitioners are lacking tools which will allow them to ensure that the models learn a given body of knowledge reliably and consistently. To this end, we propose Active Reading: a framework where we train models to study a given set of material with self-generated learning strategies. First, we demonstrate models trained with Active Reading on expert domains absorb significantly more knowledge than vanilla finetuning and other data augmentations. We train expert 8B models that achieve 66% on a Wikipedia-grounded subset of SimpleQA (+313% relative over vanilla finetuning) and 26% on FinanceBench (+160% relative over vanilla finetuning) by applying Active Reading to the source documents for each benchmark. Finally, we show that Active Reading can be utilized at pre-training scale to build more factual models. As a demonstration of this, we release Meta WikiExpert-8B, a Wikipedia-expert model trained on 1 trillion generated tokens, which outcompetes models with hundreds of billions of parameters on factual QA.

Fine-tuning large language models (LLMs) under resource constraints is a significant challenge in deep learning. Low-Rank Adaptation (LoRA), pruning, and quantization are all effective methods for improving resource efficiency. However, combining them directly often results in suboptimal performance, especially with uniform quantization across all model layers. This is due to the complex, uneven interlayer relationships introduced by pruning, necessitating more refined quantization strategies. To address this, we propose AutoMixQ, an end-to-end optimization framework that selects optimal quantization configurations for each LLM layer. AutoMixQ leverages lightweight performance models to guide the selection process, significantly reducing time and computational resources compared to exhaustive search methods. By incorporating Pareto optimality, AutoMixQ balances memory usage and performance, approaching the upper bounds of model capability under strict resource constraints. Our experiments on widely used benchmarks show that AutoMixQ reduces memory consumption while achieving superior performance. For example, at a 30\% pruning rate in LLaMA-7B, AutoMixQ achieved 66.21\% on BoolQ compared to 62.45\% for LoRA and 58.96\% for LoftQ, while reducing memory consumption by 35.5\% compared to LoRA and 27.5\% compared to LoftQ.

We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which agents diagnose failures of the current program and synthesize candidate updates, retaining only updates that improve retrieval quality under the resulting index. We evaluate AutoIndex on CRUMB, a benchmark of heterogeneous retrieval tasks, with BM25 held fixed across all experiments. The learned programs improve recall over a static full-document BM25 baseline on all 8 tasks, with average gains of +8.4% in Recall@100 and +8.3% in nDCG@10, and largest gains of +30.5% in Recall@100 and +43.6% in nDCG@10. These results suggest that document representation should not be treated as a fixed preprocessing choice made before retrieval begins, but as an explicit optimization target. Code to reproduce our results is available at https://github.com/auto-index/autoindex.

The learning and deployment of long-LLMs remains a challenging problem despite recent progresses. In this work, we argue that the long-LLMs are not a necessity to solve long-context tasks, as common long-context tasks are short-context solvable, i.e. they can be solved by purely working with oracle short-contexts within the long-context tasks' inputs. On top of this argument, we propose a framework called LC-Boost (Long-Context Bootstrapper), which enables a short-LLM to address the long-context tasks in a bootstrapping manner. In our framework, the short-LLM prompts itself to reason for two critical decisions: 1) how to access to the appropriate part of context within the input, 2) how to make effective use of the accessed context. By adaptively accessing and utilizing the context based on the presented tasks, LC-Boost can serve as a general framework to handle diversified long-context processing problems. We comprehensively evaluate different types of tasks from popular long-context benchmarks, where LC-Boost is able to achieve a substantially improved performance with a much smaller consumption of resource.

Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal throughput for inference serving. However, due to the unpredictability of LLM execution, the first-come-first-serve (FCFS) scheduling policy employed by current LLM serving systems suffers from head-of-line (HoL) blocking issues and long job response times. In this paper, we propose a new efficient LLM inference serving framework, named ALISE. The key design paradigm of ALISE is to leverage a novel speculative scheduler by estimating the execution time for each job and exploiting such prior knowledge to assign appropriate job priority orders, thus minimizing potential queuing delays for heterogeneous workloads. Furthermore, to mitigate the memory overhead of the intermediate key-value (KV) cache, we employ a priority-based adaptive memory management protocol and quantization-based compression techniques. Evaluations demonstrate that in comparison to the state-of-the-art solution vLLM, ALISE improves the throughput of inference serving by up to 1.8x and 2.1x under the same latency constraint on the Alpaca and ShareGPT datasets, respectively.

Mixture-of-Experts (MoE) models enable scalable performance but face severe memory constraints on edge devices. Existing offloading strategies struggle with I/O bottlenecks due to the dynamic, low-information nature of autoregressive expert activation. In this paper, we propose to repurpose Speculative Decoding (SD) not merely as a compute accelerator, but as an informative lookahead sensor for memory management, supported by our theoretical and empirical analyses. Hence, we introduce MoE-SpAc, an MoE inference framework that integrates a Speculative Utility Estimator to track expert demand, a Heterogeneous Workload Balancer to dynamically partition computation via online integer optimization, and an Asynchronous Execution Engine to unify the prefetching and eviction in the same utility space. Extensive experiments on seven benchmarks demonstrate that MoE-SpAc achieves a 42% improvement in TPS over the SOTA SD-based baseline, and an average 4.04x speedup over all standard baselines. Code is available at https://github.com/lshAlgorithm/MoE-SpAc .

Retrieval-based language models (R-LM) model the probability of natural language text by combining a standard language model (LM) with examples retrieved from an external datastore at test time. While effective, a major bottleneck of using these models in practice is the computationally costly datastore search, which can be performed as frequently as every time step. In this paper, we present RetoMaton - retrieval automaton - which approximates the datastore search, based on (1) saving pointers between consecutive datastore entries, and (2) clustering of entries into "states". This effectively results in a weighted finite automaton built on top of the datastore, instead of representing the datastore as a flat list. The creation of the automaton is unsupervised, and a RetoMaton can be constructed from any text collection: either the original training corpus or from another domain. Traversing this automaton at inference time, in parallel to the LM inference, reduces its perplexity by up to 1.85, or alternatively saves up to 83% of the nearest neighbor searches over kNN-LM (Khandelwal et al., 2020) without hurting perplexity. Our code and trained models are available at https://github.com/neulab/retomaton .

The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV) caching, which accelerates decoding but quickly exhausts GPU memory. In this paper, we introduce the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference. Based on this framework, we derive rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth. This result offers a powerful tool for system deployment, potentially addressing the core challenge of GPU provisioning. By combining an estimated request arrival rate with our derived stable service rate, operators can calculate the necessary cluster size to avoid both costly over-purchasing and performance-violating under-provisioning. We further validate our theoretical predictions through extensive experiments in real GPU production environments. Our results show that the predicted stability conditions are highly accurate, with deviations typically within 10%.

Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LLM routing. It comprises over 400K instances from 21 datasets and 33 models. Moreover, it provides comprehensive metrics for both performance-oriented routing and performance-cost trade-off routing, and integrates 10 representative routing baselines. Using LLMRouterBench, we systematically re-evaluate the field. While confirming strong model complementarity-the central premise of LLM routing-we find that many routing methods exhibit similar performance under unified evaluation, and several recent approaches, including commercial routers, fail to reliably outperform a simple baseline. Meanwhile, a substantial gap remains to the Oracle, driven primarily by persistent model-recall failures. We further show that backbone embedding models have limited impact, that larger ensembles exhibit diminishing returns compared to careful model curation, and that the benchmark also enables latency-aware analysis. All code and data are available at https://github.com/ynulihao/LLMRouterBench.

Database knob tuning is a critical challenge in the database community, aiming to optimize knob values to enhance database performance for specific workloads. DBMS often feature hundreds of tunable knobs, posing a significant challenge for DBAs to recommend optimal configurations. Consequently, many machine learning-based tuning methods have been developed to automate this process. Despite the introduction of various optimizers, practical applications have unveiled a new problem: they typically require numerous workload runs to achieve satisfactory performance, a process that is both time-consuming and resource-intensive. This inefficiency largely stems from the optimal configuration often being substantially different from the default setting, necessitating multiple iterations during tuning. Recognizing this, we argue that an effective starting point could significantly reduce redundant exploration in less efficient areas, thereby potentially speeding up the tuning process for the optimizers. Based on this assumption, we introduce LLMTune, a large language model-based configuration generator designed to produce an initial, high-quality configuration for new workloads. These generated configurations can then serve as starting points for various base optimizers, accelerating their tuning processes. To obtain training data for LLMTune's supervised fine-tuning, we have devised a new automatic data generation framework capable of efficiently creating a large number of <workload, configuration> pairs. We have conducted thorough experiments to evaluate LLMTune's effectiveness with different workloads, such as TPC-H and JOB. In comparison to leading methods, LLMTune demonstrates a quicker ability to identify superior configurations. For instance, with the challenging TPC-H workload, our LLMTune achieves a significant 15.6x speed-up ratio in finding the best-performing configurations.

Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at each layer, limiting overall efficiency. In this work, we propose SlimInfer, an innovative framework that aims to accelerate inference by directly pruning less critical prompt tokens during the forward pass. Our key insight is an information diffusion phenomenon: As information from critical tokens propagates through layers, it becomes distributed across the entire sequence. This diffusion process suggests that LLMs can maintain their semantic integrity when excessive tokens, even including these critical ones, are pruned in hidden states. Motivated by this, SlimInfer introduces a dynamic fine-grained pruning mechanism that accurately removes redundant tokens of hidden state at intermediate layers. This layer-wise pruning naturally enables an asynchronous KV cache manager that prefetches required token blocks without complex predictors, reducing both memory usage and I/O costs. Extensive experiments show that SlimInfer can achieve up to 2.53times time-to-first-token (TTFT) speedup and 1.88times end-to-end latency reduction for LLaMA3.1-8B-Instruct on a single RTX 4090, without sacrificing performance on LongBench. Our code will be released upon acceptance.

LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms. Traditional approaches rely on procedural JSON-based function calling, which often struggles with long-horizon tasks due to fragile multi-turn dependencies and context drift. In this paper, we present CaveAgent, a framework that transforms the paradigm from "LLM-as-Text-Generator" to "LLM-as-Runtime-Operator." We introduce a Dual-stream Context Architecture that decouples state management into a lightweight semantic stream for reasoning and a persistent, deterministic Python Runtime stream for execution. In addition to leveraging code generation to efficiently resolve interdependent sub-tasks (e.g., loops, conditionals) in a single step, we introduce Stateful Runtime Management in CaveAgent. Distinct from existing code-based approaches that remain text-bound and lack the support for external object injection and retrieval, CaveAgent injects, manipulates, and retrieves complex Python objects (e.g., DataFrames, database connections) that persist across turns. This persistence mechanism acts as a high-fidelity external memory to eliminate context drift, avoid catastrophic forgetting, while ensuring that processed data flows losslessly to downstream applications. Comprehensive evaluations on Tau^2-bench, BFCL and various case studies across representative SOTA LLMs demonstrate CaveAgent's superiority. Specifically, our framework achieves a 10.5\% success rate improvement on retail tasks and reduces total token consumption by 28.4\% in multi-turn scenarios. On data-intensive tasks, direct variable storage and retrieval reduces token consumption by 59\%, allowing CaveAgent to handle large-scale data that causes context overflow failures in both JSON-based and Code-based agents.

We introduce Trove, an easy-to-use open-source retrieval toolkit that simplifies research experiments without sacrificing flexibility or speed. For the first time, we introduce efficient data management features that load and process (filter, select, transform, and combine) retrieval datasets on the fly, with just a few lines of code. This gives users the flexibility to easily experiment with different dataset configurations without the need to compute and store multiple copies of large datasets. Trove is highly customizable: in addition to many built-in options, it allows users to freely modify existing components or replace them entirely with user-defined objects. It also provides a low-code and unified pipeline for evaluation and hard negative mining, which supports multi-node execution without any code changes. Trove's data management features reduce memory consumption by a factor of 2.6. Moreover, Trove's easy-to-use inference pipeline incurs no overhead, and inference times decrease linearly with the number of available nodes. Most importantly, we demonstrate how Trove simplifies retrieval experiments and allows for arbitrary customizations, thus facilitating exploratory research.

The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on an accurate estimate of the memory requirements of requests. However, due to the diversity in request output lengths, existing frameworks tend to adopt aggressive or conservative schedulers, which often result in significant overestimation or underestimation of memory consumption. Consequently, they suffer from harmful request evictions or prolonged queuing times, failing to achieve satisfactory throughput under strict Service Level Agreement (SLA) guarantees (a.k.a. goodput), across various LLM application scenarios with differing input-output length distributions. To address this issue, we propose a novel Past-Future scheduler that precisely estimates the peak memory resources required by the running batch via considering the historical distribution of request output lengths and calculating memory occupancy at each future time point. It adapts to applications with all types of input-output length distributions, balancing the trade-off between request queuing and harmful evictions, thereby consistently achieving better goodput. Furthermore, to validate the effectiveness of the proposed scheduler, we developed a high-performance LLM serving framework, LightLLM, that implements the Past-Future scheduler. Compared to existing aggressive or conservative schedulers, LightLLM demonstrates superior goodput, achieving up to 2-3times higher goodput than other schedulers under heavy loads. LightLLM is open source to boost the research in such direction (https://github.com/ModelTC/lightllm).

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and high memory overhead when processing lengthy inputs. To mitigate these issues, we introduce a novel context compression pipeline, called Intermediate Layer Retrieval (ILRe), which determines one intermediate decoder layer offline, encodes context by streaming chunked prefill only up to that layer, and recalls tokens by the attention scores between the input query and full key cache in that specified layer. In particular, we propose a multi-pooling kernels allocating strategy in the token recalling process to maintain the completeness of semantics. Our approach not only reduces the prefilling complexity from O(L^2) to O(L), but also achieves performance comparable to or better than the full context in the long context scenarios. Without additional post training or operator development, ILRe can process a single 1M tokens request in less than half a minute (speedup approx 180times) and scores RULER-1M benchmark of approx 79.8 with model Llama-3.1-UltraLong-8B-1M-Instruct on a Huawei Ascend 910B NPU.

LLM-based code agents navigate repositories through keyword search but miss the structural relationships, such as call graphs, inheritance hierarchies, and configuration dependencies, that define how software actually works. This makes agent navigation stochastic and difficult to reproduce across runs. We investigate whether lightweight static analysis can provide deterministic anchors for these agents: stable structural facts injected as plain-text comments that constrain probabilistic exploration and make navigation more predictable. Starting from a strong baseline, Codex from OpenAI, we systematically inject varying granularities of structural annotations and measure their effects on localization, trajectory behavior, and run-to-run stability. Our study identifies what we call the deterministic anchoring effect: static structure helps less by making agents "smarter" and more by making their navigation disciplined and reproducible. Three observations support this finding: (1) Anchoring works: lightweight call/inheritance topology improves function-level localization (+2.2pp Func@5) and shortens trajectories (-1.6 interaction rounds); (2) Anchoring is scale-sensitive: the optimal granularity and directionality depend on repository characteristics, where denser semantics show diminishing returns and hub-heavy projects benefit from inverse-only links that expose "who-calls-me" without forward edges; (3) Anchoring stabilizes: tags raise link-following rate from 0.15-0.18 to 0.21-0.24, roughly halve run-to-run variance, and improve single-run reliability (Pass@1 +3.4 pp) on medium-scale repositories, at the cost of roughly 10% more input tokens. These observations suggest practical guidelines: default to lightweight topology on medium projects, prune forward edges in large repositories, and reserve dense tags for implicit-dependency cases.

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple queries. However, the LLMs still need to encode the entire context for each query, leading to redundant computation. In this paper, we investigate a new strategy to eliminate such inefficiency, where the KV cache of each document is precomputed independently. During inference, the KV caches of retrieved documents are concatenated, allowing the model to reuse cached representations instead of recomputing them. To mitigate the performance degradation when using KV caches computed independently for each document, KVLink introduces two key techniques: adjusting positional embeddings of the KV cache at inference to match the global position after concatenation, and using trainable special tokens to restore self-attention across independently encoded documents. Experiments across 7 datasets demonstrate that KVLink improves question answering accuracy by an average of 4% over state-of-the-art methods. Furthermore, by leveraging precomputed KV caches, our approach reduces time-to-first-token by up to 96% compared to standard LLM inference, making it a scalable and efficient solution for context reuse. Additionally, KVLink can be combined with KV cache compression to further save cache loading and storage overhead while outperforming the baselines.

LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contain latent semantic parallelism--decomposable structures where subtasks can be executed independently to reduce latency while preserving meaning. We introduce PARALLELPROMPT, the first benchmark for measuring intra-query parallelism in natural user prompts. Our dataset comprises over 37,000 real-world prompts from public LLM chat logs, each annotated with a structured schema capturing task templates, shared context, and iteration inputs. These schemas are extracted using LLM-assisted prompting with rule-based multilingual validation. To evaluate the benefits of decomposition, we provide an execution suite that benchmarks serial vs. parallel strategies, measuring latency, structural adherence, and semantic fidelity. Our results show that intra-query parallelism can be successfully parsed in over 75% of curated datasets, unlocking up to 5x speedups on tasks like translation, comprehension, and comparative analysis, with minimal quality degradation. By releasing this benchmark, curation pipeline, and evaluation suite, we provide the first standardized testbed for studying structure-aware execution in LLM serving pipelines.

Information retrieval in Large Language Models (LLMs) is increasingly recognized as intertwined with generation capabilities rather than mere lookup. While longer contexts are often assumed to improve retrieval, the effects of intra-context interference remain understudied. To address this, we adapt the proactive interference (PI) paradigm from cognitive science, where earlier information disrupts recall of newer updates. In humans, susceptibility to such interference is inversely linked to working memory capacity. We introduce PI-LLM, an evaluation that sequentially streams semantically related key-value updates and queries only the final values. Although these final values are clearly positioned just before the query, LLM retrieval accuracy declines log-linearly toward zero as interference accumulates; errors arise from retrieving previously overwritten values. Attempts to mitigate interference via prompt engineering (e.g., instructing models to ignore earlier input) yield limited success. These findings reveal a fundamental constraint on LLMs' ability to disentangle interference and flexibly manipulate information, suggesting a working memory bottleneck beyond mere context access. This calls for approaches that strengthen models' ability to suppress irrelevant content during retrieval.

KV caching significantly improves the efficiency of Large Language Model (LLM) inference by storing attention states from previously processed tokens, enabling faster generation of subsequent tokens. However, as sequence length increases, the KV cache quickly becomes a major memory bottleneck. To address this, we propose PagedEviction, a novel fine-grained, structured KV cache pruning strategy that enhances the memory efficiency of vLLM's PagedAttention. Unlike existing approaches that rely on attention-based token importance or evict tokens across different vLLM pages, PagedEviction introduces an efficient block-wise eviction algorithm tailored for paged memory layouts. Our method integrates seamlessly with PagedAttention without requiring any modifications to its CUDA attention kernels. We evaluate PagedEviction across Llama-3.1-8B-Instruct, Llama-3.2-1B-Instruct, and Llama-3.2-3B-Instruct models on the LongBench benchmark suite, demonstrating improved memory usage with better accuracy than baselines on long context tasks.

Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when the context is reused as the prefix of another LLM input. However, the reused text chunks are not always the input prefix, and when they are not, their precomputed KV caches cannot be directly used since they ignore the text's cross-attention with the preceding text in the LLM input. Thus, the benefits of reusing KV caches remain largely unrealized. This paper tackles just one question: when an LLM input contains multiple text chunks, how to quickly combine their precomputed KV caches in order to achieve the same generation quality as the expensive full prefill (i.e., without reusing KV cache)? We present CacheBlend, a scheme that reuses the pre-computed KV caches, regardless prefix or not, and selectively recomputes the KV values of a small subset of tokens to partially update each reused KV cache. In the meantime,the small extra delay for recomputing some tokens can be pipelined with the retrieval of KV caches within the same job,allowing CacheBlend to store KV caches in slower devices with more storage capacity while retrieving them without increasing the inference delay. By comparing CacheBlend with the state-of-the-art KV cache reusing schemes on three open-source LLMs of various sizes and four popular benchmark datasets of different tasks, we show that CacheBlend reduces time-to-first-token (TTFT) by 2.2-3.3X and increases the inference throughput by 2.8-5X, compared with full KV recompute, without compromising generation quality or incurring more storage cost.

Powered by a large language model (LLM), a web browsing agent operates web browsers in a human-like manner and offers a highly transparent path toward automating a wide range of everyday tasks. As web agents become increasingly capable and demonstrate proficiency in general browsing tasks, a critical question emerges: Can they go beyond general browsing to robustly handle tasks that are tedious and complex, or chores that humans often avoid doing themselves? In this paper, we introduce WebChoreArena, a new fully reproducible benchmark comprising 532 carefully curated tasks designed to extend the scope of WebArena beyond general browsing to more labor-intensive and tedious tasks. WebChoreArena systematically integrates three key challenges: (i) Massive Memory tasks requiring accurate retrieval of large amounts of information in the observations, (ii) Calculation tasks demanding precise mathematical reasoning, and (iii) Long-Term Memory tasks necessitating long-term memory across multiple webpages. Built on top of the fully reproducible and widely adopted four WebArena simulation environments, WebChoreArena ensures strict reproducibility and enables fair, direct comparisons with the established WebArena benchmark, offering key insights into agent progress. Our experimental results demonstrate that as LLMs evolve, represented by GPT-4o, Claude 3.7 Sonnet, and Gemini 2.5 Pro, significant improvements in performance are observed on WebChoreArena. These findings suggest that WebChoreArena is well-suited to measure the advancement of state-of-the-art LLMs with greater clarity. Nevertheless, the results also indicate that even with Gemini 2.5 Pro, there remains substantial room for improvement compared to WebArena, highlighting the increased challenges posed by WebChoreArena.