Daily Papers

Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets. A key challenge is delayed query: decisive cues may appear briefly, yet many subsequent updates occur before the query arrives, increasing the risk that those cues are evicted or diluted under bounded memory. We propose ProtoKV, a constant-footprint SVU memory that represents far history as a fixed-capacity summary state rather than retaining token instances. ProtoKV keeps an exact near-window KV cache and aggregates older content into a semantic-spatial prototype bank with residual statistics. At query time, each prototype is exposed through a bounded pseudo-token interface that is drop-in compatible with standard attention. Under matched budgets and comparable query-time cost, ProtoKV improves accuracy by up to 12.5 points over token-retention baselines on SVU benchmarks in the long-delay regime, with gains that grow as query delay increases.

Deep pretrained transformer networks are effective at various ranking tasks, such as question answering and ad-hoc document ranking. However, their computational expenses deem them cost-prohibitive in practice. Our proposed approach, called PreTTR (Precomputing Transformer Term Representations), considerably reduces the query-time latency of deep transformer networks (up to a 42x speedup on web document ranking) making these networks more practical to use in a real-time ranking scenario. Specifically, we precompute part of the document term representations at indexing time (without a query), and merge them with the query representation at query time to compute the final ranking score. Due to the large size of the token representations, we also propose an effective approach to reduce the storage requirement by training a compression layer to match attention scores. Our compression technique reduces the storage required up to 95% and it can be applied without a substantial degradation in ranking performance.

BERT-based information retrieval models are expensive, in both time (query latency) and computational resources (energy, hardware cost), making many of these models impractical especially under resource constraints. The reliance on a query encoder that only performs tokenization and on the pre-processing of passage representations at indexing, has allowed the recently proposed TILDE method to overcome the high query latency issue typical of BERT-based models. This however is at the expense of a lower effectiveness compared to other BERT-based re-rankers and dense retrievers. In addition, the original TILDE method is characterised by indexes with a very high memory footprint, as it expands each passage into the size of the BERT vocabulary. In this paper, we propose TILDEv2, a new model that stems from the original TILDE but that addresses its limitations. TILDEv2 relies on contextualized exact term matching with expanded passages. This requires to only store in the index the score of tokens that appear in the expanded passages (rather than all the vocabulary), thus producing indexes that are 99% smaller than those of TILDE. This matching mechanism also improves ranking effectiveness by 24%, without adding to the query latency. This makes TILDEv2 the state-of-the-art passage re-ranking method for CPU-only environments, capable of maintaining query latency below 100ms on commodity hardware.

Many modern retrieval problems are set-valued: given a broad intent, the system must return a collection of results that optimizes higher-order properties (e.g., diversity, coverage, complementarity, coherence) while remaining grounded with respect to a fixed database. Set-valued objectives are typically non-decomposable and are not captured by existing supervised (query, content) datasets which only prioritize top-1 retrieval. Consequently, fan-out retrieval is often employed to generate diverse subqueries to retrieve item sets. While reinforcement learning (RL) can optimize set-level objectives via interaction, deploying an RL-tuned LLM for fan-out retrieval is prohibitively expensive at inference time. Conversely, diffusion-based generative retrieval enables efficient single-pass fan-out in embedding space, but requires objective-aligned training targets. To address these issues, we propose R4T (Retrieve-for-Train), which uses RL once as an objective transducer in a three-step process: (i) train a fan-out LLM with composite set-level rewards, (ii) synthesize objective-consistent training pairs, and (iii) train a lightweight diffusion retriever to model the conditional distribution of set-valued outputs. Across large-scale fashion and music benchmarks consisting of curated item sets, we show that R4T improves retrieval quality relative to strong baselines while reducing query-time fan-out latency by an order of magnitude.

Retrieval-Augmented Generation (RAG) offers an effective approach for large language models to access external knowledge. However, existing methods rely on dense similarity retrieval and face inherent limitations in handling structured constraints and multi-hop reasoning. Incorporating knowledge graphs partially alleviates these issues, but at the cost of semantic fragmentation, high maintenance overhead, and difficult incremental updates. This paper introduces SAG (SQLRetrieval Augmented Generation), a structured architecture for retrieval and agent systems. Instead of pre-building a global static graph, SAG converts each chunk into one semantically complete event and a set of indexing entities, then uses SQL join queries to dynamically link events that share entities into local hyperedges,constructing, at query time, a dynamically instantiated local index structure. This design avoids the need for global graph rebuilding and ongoing maintenance; the system naturally supports incremental writes, concurrent processing, and continuous scaling through its reliance on standard database infrastructure. Across HotpotQA, 2WikiMultiHop, and MuSiQue, three standard multi-hop benchmarks,SAG achieves the best results on 8 out of 9 Recall@K metrics, reaching 80.0% Recall@5 on MuSiQue, the benchmark with the highest multi-hop reasoning demands.SAG has also been deployed at a production scale of hundreds of millions of data items, with online retrieval latency kept within seconds. Project site and code are available at https://github.com/Zleap-AI/SAG-Benchmark.

Retrieval and ranking models are the backbone of many applications such as web search, open domain QA, or text-based recommender systems. The latency of neural ranking models at query time is largely dependent on the architecture and deliberate choices by their designers to trade-off effectiveness for higher efficiency. This focus on low query latency of a rising number of efficient ranking architectures make them feasible for production deployment. In machine learning an increasingly common approach to close the effectiveness gap of more efficient models is to apply knowledge distillation from a large teacher model to a smaller student model. We find that different ranking architectures tend to produce output scores in different magnitudes. Based on this finding, we propose a cross-architecture training procedure with a margin focused loss (Margin-MSE), that adapts knowledge distillation to the varying score output distributions of different BERT and non-BERT passage ranking architectures. We apply the teachable information as additional fine-grained labels to existing training triples of the MSMARCO-Passage collection. We evaluate our procedure of distilling knowledge from state-of-the-art concatenated BERT models to four different efficient architectures (TK, ColBERT, PreTT, and a BERT CLS dot product model). We show that across our evaluated architectures our Margin-MSE knowledge distillation significantly improves re-ranking effectiveness without compromising their efficiency. Additionally, we show our general distillation method to improve nearest neighbor based index retrieval with the BERT dot product model, offering competitive results with specialized and much more costly training methods. To benefit the community, we publish the teacher-score training files in a ready-to-use package.

Retrieval-Augmented Generation (RAG) often relies on large vector databases and cross-encoders tuned for large-scale corpora, which can be excessive for small, domain-specific collections. We present MODE (Mixture of Document Experts), a lightweight alternative that replaces fine-grained nearest-neighbor search with cluster-and-route retrieval. Documents are embedded, grouped into semantically coherent clusters, and represented by cached centroids. At query time, we route to the top centroid(s) and retrieve context only within those clusters, eliminating external vector-database infrastructure and reranking while keeping latency low. On HotpotQA and SQuAD corpora with 100-500 chunks, MODE matches or exceeds a dense-retrieval baseline in answer quality while reducing end-to-end retrieval time. Ablations show that cluster granularity and multi-cluster routing control the recall/precision trade-off, and that tighter clusters improve downstream accuracy. MODE offers a practical recipe for small and medium corpora where simplicity, speed, and topical focus matter.

Retrieving external knowledge is essential for solving real-world tasks, yet it remains challenging when the relationship between a query and its relevant knowledge involves implicit and complex reasoning beyond surface-level semantic or lexical matching (e.g., mathematical problems relying on the same theorem or coding requiring deep reasoning). Existing approaches primarily rely on query-side reasoning (e.g., query rewriting), which introduces significant online latency and underutilizes the opportunity to perform reasoning over the knowledge corpus itself (i.e., index-side reasoning). In this paper, we propose RL-Index, an agentic indexing framework that formulates retrieval index reasoning as a reinforcement learning problem. Instead of performing reasoning at query time, RL-Index shifts reasoning to the indexing stage by augmenting documents with LLM-generated rationales that explicitly encode the latent query-knowledge relationship. To optimize the quality of these rationales, we employ Group Relative Policy Optimization (GRPO) and use retrieval similarity as a verifiable reward signal, enabling direct optimization of indexing decisions for retrieval effectiveness. Extensive experiments on the BRIGHT benchmark demonstrate that RL-Index consistently improves both retrieval and downstream question-answering performance, while significantly reducing online inference latency. Moreover, the learned rationale augmentation generalizes across diverse retrievers and generators, highlighting its robustness as a plug-and-play indexing strategy across different retrieval systems.

Transformer-based text embedding models have improved their performance on benchmarks like MIRACL and BEIR by increasing their parameter counts. However, this scaling approach introduces significant deployment challenges, including increased inference latency and memory usage. These challenges are particularly severe in retrieval-augmented generation (RAG) applications, where large models' increased memory requirements constrain dataset ingestion capacity, and their higher latency directly impacts query-time performance. While causal language models have addressed similar efficiency challenges using Mixture of Experts (MoE) architectures, this approach hasn't been successfully adapted to the general text embedding setting. In this paper, we introduce Nomic Embed v2, the first general purpose MoE text embedding model. Our model outperforms models in the same parameter class on both monolingual and multilingual benchmarks while also maintaining competitive performance with models twice its size. We open-source all code, models, and evaluation data to ensure full reproducibility of our training pipeline.

We present an algorithmic framework for incremental maintenance of first sheaf cohomology H^1(X; F) on dynamically evolving 1-dimensional cellular complexes equipped with finite-dimensional cellular sheaves. The classical computation of H^1 via factorization of the coboundary matrix requires O(n^3) time; when the complex evolves with a stream of m edits, full recomputation after each edit costs O(mn^3). Under a bounded local geometry assumption -- bounded cell size v_{max}, bounded stalk dimension d, and bounded nerve degree D -- each edit (vertex insertion, edge insertion, restriction map update) affects only a bounded set of local coboundary blocks. The algorithm therefore processes lazy streaming edits in O(1) time with respect to the total complex size n (with cost polynomial in the local geometry parameters v_{max}, d, and D, which are treated as constants independent of n), deferring local eigensolves and Mayer-Vietoris global assembly to synchronization points (Flush). At synchronization, the maintained state agrees with the corresponding batch assembly of the partitioned sheaf model; we observe zero measured drift in all batch-verified runs (through V = 10^6). We also give an amortized O(|E|) streaming construction for the cellular decomposition and discuss an adversarial algebraic-RAM barrier arguing that unpartitioned non-trivial sheaves (d geq 2, non-identity restriction maps) do not admit the same locality. Experiments on Barabasi-Albert graphs with up to 5 times 10^6 vertices and 1.7 times 10^7 streaming edits show 35 μs median lazy per-edit update latency (excluding flush); query time (global assembly at synchronization) is O(n) per flush in the implemented full-traversal path. Exact synchronization costs are reported separately.

In the dynamic landscape of large-scale web search, Query-Driven Text Summarization (QDTS) aims to generate concise and informative summaries from textual documents based on a given query, which is essential for improving user engagement and facilitating rapid decision-making. Traditional extractive summarization models, based primarily on ranking candidate summary segments, have been the dominant approach in industrial applications. However, these approaches suffer from two key limitations: 1) The multi-stage pipeline often introduces cumulative information loss and architectural bottlenecks due to its weakest component; 2) Traditional models lack sufficient semantic understanding of both user queries and documents, particularly when dealing with complex search intents. In this study, we propose a novel framework to pioneer the application of generative models to address real-time QDTS in industrial web search. Our approach integrates large model distillation, supervised fine-tuning, direct preference optimization, and lookahead decoding to transform a lightweight model with only 0.1B parameters into a domain-specialized QDTS expert. Evaluated on multiple industry-relevant metrics, our model outperforms the production baseline and achieves a new state of the art. Furthermore, it demonstrates excellent deployment efficiency, requiring only 334 NVIDIA L20 GPUs to handle \textasciitilde50,000 queries per second under 55~ms average latency per query.

Recent advances in retrieval models based on learned sparse representations generated by transformers have led us to, once again, consider score-at-a-time query evaluation techniques for the top-k retrieval problem. Previous studies comparing document-at-a-time and score-at-a-time approaches have consistently found that the former approach yields lower mean query latency, although the latter approach has more predictable query latency. In our experiments with four different retrieval models that exploit representational learning with bags of words, we find that transformers generate "wacky weights" that appear to greatly reduce the opportunities for skipping and early exiting optimizations that lie at the core of standard document-at-a-time techniques. As a result, score-at-a-time approaches appear to be more competitive in terms of query evaluation latency than in previous studies. We find that, if an effectiveness loss of up to three percent can be tolerated, a score-at-a-time approach can yield substantial gains in mean query latency while at the same time dramatically reducing tail latency.

Enterprise ERP systems managing hundreds of thousands of employee records face critical data quality challenges when human resources departments perform decentralized manual entry across multiple languages. We present an end-to-end pipeline combining automated data cleaning with LLM-driven SQL query generation, deployed on a production system managing 240,000 employee records over six months. The system operates in two integrated stages: a multi-stage cleaning pipeline that performs translation normalization, spelling correction, and entity deduplication during periodic synchronization from Microsoft SQL Server to PostgreSQL; and a retrieval-augmented generation framework powered by GPT-4o that translates natural-language questions in Turkish, Russian, and English into validated SQL queries. The query engine employs LangChain orchestration, FAISS vector similarity search, and few-shot learning with 500+ validated examples. Our evaluation demonstrates 92.5% query validity, 95.1% schema compliance, and 90.7\% semantic accuracy on 2,847 production queries. The system reduces query turnaround time from 2.3 days to under 5 seconds while maintaining 99.2% uptime, with GPT-4o achieving 46% lower latency and 68% cost reduction versus GPT-3.5. This modular architecture provides a reproducible framework for AI-native enterprise data governance, demonstrating real-world viability at enterprise scale with 4.3/5.0 user satisfaction.

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform exhaustive retrieval across the entire storage layer regardless of query characteristics. This brute-force approach creates severe latency bottlenecks as memory grows, hindering real-time agent interactions. We propose SwiftMem, a query-aware agentic memory system that achieves sub-linear retrieval through specialized indexing over temporal and semantic dimensions. Our temporal index enables logarithmic-time range queries for time-sensitive retrieval, while the semantic DAG-Tag index maps queries to relevant topics through hierarchical tag structures. To address memory fragmentation during growth, we introduce an embedding-tag co-consolidation mechanism that reorganizes storage based on semantic clusters to improve cache locality. Experiments on LoCoMo and LongMemEval benchmarks demonstrate that SwiftMem achieves 47times faster search compared to state-of-the-art baselines while maintaining competitive accuracy, enabling practical deployment of memory-augmented LLM agents.

Large language models (LLMs) have demonstrated strong effectiveness and robustness while fine-tuned as dense retrievers. However, their large parameter size brings significant inference time computational challenges, including high encoding costs for large-scale corpora and increased query latency, limiting their practical deployment. While smaller retrievers offer better efficiency, they often fail to generalize effectively with limited supervised fine-tuning data. In this work, we introduce DRAMA, a training framework that leverages LLMs to train smaller generalizable dense retrievers. In particular, we adopt pruned LLMs as the backbone and train on diverse LLM-augmented data in a single-stage contrastive learning setup. Experiments show that DRAMA offers better multilingual and long-context capabilities than traditional encoder-based retrievers, and achieves strong performance across multiple tasks and languages. These highlight the potential of connecting the training of smaller retrievers with the growing advancements in LLMs, bridging the gap between efficiency and generalization.

Retrieval-Augmented Generation for software engineering often relies on vector similarity search, which captures topical similarity but can fail on multi-hop architectural reasoning such as controller to service to repository chains, interface-driven wiring, and inheritance. This paper benchmarks three retrieval pipelines on Java codebases (Shopizer, with additional runs on ThingsBoard and OpenMRS Core): (A) vector-only No-Graph RAG, (B) an LLM-generated knowledge graph RAG (LLM-KB), and (C) a deterministic AST-derived knowledge graph RAG (DKB) built with Tree-sitter and bidirectional traversal. Using 15 architecture and code-tracing queries per repository, we measure indexing time, query latency, corpus coverage, cost, and answer correctness. DKB builds its graph in seconds, while LLM-KB requires much longer graph generation. LLM-KB also shows indexing incompleteness: on Shopizer, 377 files are skipped or missed, reducing embedded chunk coverage and graph size compared to DKB. End-to-end cost is modest for DKB relative to the vector-only baseline but much higher for LLM-KB, especially as repository scale increases. Query latency is similar for No-Graph and DKB, while LLM-KB is slower and more variable. On the Shopizer question suite, DKB achieves the highest correctness, LLM-KB is close behind, and the vector-only baseline performs worst on upstream architectural queries and has the highest hallucination risk. Overall, deterministic AST-derived graphs provide more reliable coverage and multi-hop grounding than LLM-extracted graphs at substantially lower indexing cost.

Structured LLM workflows, where specialized LLM sub-agents execute according to a predefined graph, have become a powerful abstraction for solving complex tasks. Optimizing such workflows, i.e., selecting configurations for each sub-agent to balance accuracy and latency, is challenging due to the combinatorial design space over model choices, reasoning budgets, and workflow structures. Existing cost-aware methods largely treat workflow optimization as a routing problem, selecting a configuration at inference time for each query according to the accuracy-latency objective used during training. We argue that structured LLM workflows can also be optimized from a compilation perspective: before deployment, the system can globally explore the workflow design space and construct a reusable set of workflow-level configurations spanning diverse accuracy-latency trade-offs. Drawing inspiration from machine learning compilers, we introduce FlowCompile, a structured LLM workflow compiler that performs compile-time design space exploration to identify a high-quality, reusable trade-off set. FlowCompile decomposes a workflow into sub-agents, profiles each sub-agent under diverse configurations, and composes these measurements through a structure-aware proxy to estimate workflow-level accuracy and latency. It then identifies diverse high-quality configurations in a single compile-time pass, without retraining or online adaptation. Experiments across diverse workflows and challenging benchmarks show that FlowCompile consistently outperforms heuristically optimized workflow configurations and routing-based baselines, delivering up to 6.4x speedup. The compiled configuration set further serves as a reusable optimization artifact, enabling flexible deployment under varying runtime preferences and supporting downstream selection or routing.

Analyzing large datasets requires responsive query execution, but executing SQL queries on massive datasets can be slow. This paper explores whether query execution can begin even before the user has finished typing, allowing results to appear almost instantly. We propose SpeQL, a system that leverages Large Language Models (LLMs) to predict likely queries based on the database schema, the user's past queries, and their incomplete query. Since exact query prediction is infeasible, SpeQL speculates on partial queries in two ways: 1) it predicts the query structure to compile and plan queries in advance, and 2) it precomputes smaller temporary tables that are much smaller than the original database, but are still predicted to contain all information necessary to answer the user's final query. Additionally, SpeQL continuously displays results for speculated queries and subqueries in real time, aiding exploratory analysis. A utility/user study showed that SpeQL improved task completion time, and participants reported that its speculative display of results helped them discover patterns in the data more quickly. In the study, SpeQL improves user's query latency by up to 289times and kept the overhead reasonable, at 4$ per hour.

Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM reasoning to mitigate uncertainties and reduce potential errors. However, existing research predominantly focuses on reasoning performance, often neglecting the efficiency of agentic systems. In this work, we present a comprehensive empirical study that identifies efficiency bottlenecks in web-interactive agentic systems. We decompose end-to-end latency into two primary components: LLM API latency and web environment latency. We conduct a comprehensive empirical study across 15 models and 5 providers to demonstrate high variability in API-based agentic systems. We observe that web environment latency can contribute as much as 53.7% to the overall latency in a web-based agentic system. To improve latency, we propose SpecCache, a caching framework augmented with speculative execution that can reduce web environment overhead. Extensive evaluations on two standard benchmarks show that our approach improves the cache hit rate by up to 58x compared to a random caching strategy, while reducing web environment overhead by up to 3.2x, without degrading agentic system performance.

One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content.From the perspective of a question answering system, this might comprise questions the document can potentially answer. Following this observation, we propose a simple method that predicts which queries will be issued for a given document and then expands it with those predictions with a vanilla sequence-to-sequence model, trained using datasets consisting of pairs of query and relevant documents. By combining our method with a highly-effective re-ranking component, we achieve the state of the art in two retrieval tasks. In a latency-critical regime, retrieval results alone (without re-ranking) approach the effectiveness of more computationally expensive neural re-rankers but are much faster.

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a latency-aware evaluation of representative TTS methods, we demonstrate that a compute-optimal TTS does not always result in the lowest latency in scenarios where latency is critical. To address this gap and achieve latency-optimal TTS, we propose two key approaches by optimizing the concurrency configurations: (1) branch-wise parallelism, which leverages multiple concurrent inference branches, and (2) sequence-wise parallelism, enabled by speculative decoding. By integrating these two approaches and allocating computational resources properly to each, our latency-optimal TTS enables a 32B model to reach 82.3% accuracy on MATH-500 within 1 minute and a smaller 3B model to achieve 72.4% within 10 seconds. Our work emphasizes the importance of latency-aware TTS and demonstrates its ability to deliver both speed and accuracy in latency-sensitive scenarios.

Query Auto Completion (QAC), as the starting point of information retrieval tasks, is critical to user experience. Generally it has two steps: generating completed query candidates according to query prefixes, and ranking them based on extracted features. Three major challenges are observed for a query auto completion system: (1) QAC has a strict online latency requirement. For each keystroke, results must be returned within tens of milliseconds, which poses a significant challenge in designing sophisticated language models for it. (2) For unseen queries, generated candidates are of poor quality as contextual information is not fully utilized. (3) Traditional QAC systems heavily rely on handcrafted features such as the query candidate frequency in search logs, lacking sufficient semantic understanding of the candidate. In this paper, we propose an efficient neural QAC system with effective context modeling to overcome these challenges. On the candidate generation side, this system uses as much information as possible in unseen prefixes to generate relevant candidates, increasing the recall by a large margin. On the candidate ranking side, an unnormalized language model is proposed, which effectively captures deep semantics of queries. This approach presents better ranking performance over state-of-the-art neural ranking methods and reduces sim95\% latency compared to neural language modeling methods. The empirical results on public datasets show that our model achieves a good balance between accuracy and efficiency. This system is served in LinkedIn job search with significant product impact observed.

Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved paradigm introduces substantial efficiency bottlenecks. First, we observe that both highly accurate and overly approximate retrieval methods degrade system efficiency: exact search incurs significant retrieval overhead, while coarse retrieval requires additional reasoning steps during generation. Second, we identify inefficiencies in system design, including improper scheduling and frequent retrieval stalls, which lead to cascading latency -- where even minor delays in retrieval amplify end-to-end inference time. To address these challenges, we introduce SearchAgent-X, a high-efficiency inference framework for LLM-based search agents. SearchAgent-X leverages high-recall approximate retrieval and incorporates two key techniques: priority-aware scheduling and non-stall retrieval. Extensive experiments demonstrate that SearchAgent-X consistently outperforms state-of-the-art systems such as vLLM and HNSW-based retrieval across diverse tasks, achieving up to 3.4times higher throughput and 5times lower latency, without compromising generation quality. SearchAgent-X is available at https://github.com/tiannuo-yang/SearchAgent-X.

Query rewriting aims to generate a new query that can complement the original query to improve the information retrieval system. Recent studies on query rewriting, such as query2doc (Q2D), query2expand (Q2E) and querey2cot (Q2C), rely on the internal knowledge of Large Language Models (LLMs) to generate a relevant passage to add information to the query. Nevertheless, the efficacy of these methodologies may markedly decline in instances where the requisite knowledge is not encapsulated within the model's intrinsic parameters. In this paper, we propose a novel structured query rewriting method called Crafting the Path tailored for retrieval systems. Crafting the Path involves a three-step process that crafts query-related information necessary for finding the passages to be searched in each step. Specifically, the Crafting the Path begins with Query Concept Comprehension, proceeds to Query Type Identification, and finally conducts Expected Answer Extraction. Experimental results show that our method outperforms previous rewriting methods, especially in less familiar domains for LLMs. We demonstrate that our method is less dependent on the internal parameter knowledge of the model and generates queries with fewer factual inaccuracies. Furthermore, we observe that Crafting the Path has less latency compared to the baselines.

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional generation-length-based definition breaks down: tool latency decouples inference time from generation length. We propose Timely Machine, redefining test-time as wall-clock time, where models dynamically adjust strategies based on time budgets. We introduce Timely-Eval, a benchmark spanning high-frequency tool calls, low-frequency tool calls, and time-constrained reasoning. By varying tool latency, we find smaller models excel with fast feedback through more interactions, while larger models dominate high-latency settings via superior interaction quality. Moreover, existing models fail to adapt reasoning to time budgets. We propose Timely-RL to address this gap. After cold-start supervised fine-tuning, we use reinforcement learning to enhance temporal planning. Timely-RL improves time budget awareness and consistently boosts performance across Timely-Eval. We hope our work offers a new perspective on test-time scaling for the agentic era.

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 .

Latency and efficiency issues are often overlooked when evaluating IR models based on Pretrained Language Models (PLMs) in reason of multiple hardware and software testing scenarios. Nevertheless, efficiency is an important part of such systems and should not be overlooked. In this paper, we focus on improving the efficiency of the SPLADE model since it has achieved state-of-the-art zero-shot performance and competitive results on TREC collections. SPLADE efficiency can be controlled via a regularization factor, but solely controlling this regularization has been shown to not be efficient enough. In order to reduce the latency gap between SPLADE and traditional retrieval systems, we propose several techniques including L1 regularization for queries, a separation of document/query encoders, a FLOPS-regularized middle-training, and the use of faster query encoders. Our benchmark demonstrates that we can drastically improve the efficiency of these models while increasing the performance metrics on in-domain data. To our knowledge, {we propose the first neural models that, under the same computing constraints, achieve similar latency (less than 4ms difference) as traditional BM25, while having similar performance (less than 10\% MRR@10 reduction) as the state-of-the-art single-stage neural rankers on in-domain data}.

Dense retrieval in most industries employs dual-tower architectures to retrieve query-relevant documents. Due to online deployment requirements, existing real-world dense retrieval systems mainly enhance performance by designing negative sampling strategies, overlooking the advantages of scaling up. Recently, Large Language Models (LLMs) have exhibited superior performance that can be leveraged for scaling up dense retrieval. However, scaling up retrieval models significantly increases online query latency. To address this challenge, we propose ScalingNote, a two-stage method to exploit the scaling potential of LLMs for retrieval while maintaining online query latency. The first stage is training dual towers, both initialized from the same LLM, to unlock the potential of LLMs for dense retrieval. Then, we distill only the query tower using mean squared error loss and cosine similarity to reduce online costs. Through theoretical analysis and comprehensive offline and online experiments, we show the effectiveness and efficiency of ScalingNote. Our two-stage scaling method outperforms end-to-end models and verifies the scaling law of dense retrieval with LLMs in industrial scenarios, enabling cost-effective scaling of dense retrieval systems. Our online method incorporating ScalingNote significantly enhances the relevance between retrieved documents and queries.

Complex dialog systems often use retrieved evidence to facilitate factual responses. Such RAG (Retrieval Augmented Generation) systems retrieve from massive heterogeneous data stores that are usually architected as multiple indexes or APIs instead of a single monolithic source. For a given query, relevant evidence needs to be retrieved from one or a small subset of possible retrieval sources. Complex queries can even require multi-step retrieval. For example, a conversational agent on a retail site answering customer questions about past orders will need to retrieve the appropriate customer order first and then the evidence relevant to the customer's question in the context of the ordered product. Most RAG Agents handle such Chain-of-Thought (CoT) tasks by interleaving reasoning and retrieval steps. However, each reasoning step directly adds to the latency of the system. For large models (>100B parameters) this latency cost is significant -- in the order of multiple seconds. Multi-agent systems may classify the query to a single Agent associated with a retrieval source, though this means that a (small) classification model dictates the performance of a large language model. In this work we present REAPER (REAsoning-based PlannER) - an LLM based planner to generate retrieval plans in conversational systems. We show significant gains in latency over Agent-based systems and are able to scale easily to new and unseen use cases as compared to classification-based planning. Though our method can be applied to any RAG system, we show our results in the context of Rufus -- Amazon's conversational shopping assistant.

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.

Efficient deployment of small language models (SLMs) is essential for numerous real-world applications with stringent latency constraints. While previous work on SLM design has primarily focused on reducing the number of parameters to achieve parameter-optimal SLMs, parameter efficiency does not necessarily translate into proportional real-device speed-ups. This work aims to identify the key determinants of SLMs' real-device latency and offer generalizable principles and methodologies for SLM design and training when real-device latency is the primary consideration. Specifically, we identify two central architectural factors: depth-width ratios and operator choices. The former is crucial for small-batch-size latency, while the latter affects both latency and large-batch-size throughput. In light of this, we first study latency-optimal depth-width ratios, with the key finding that although deep-thin models generally achieve better accuracy under the same parameter budget, they may not lie on the accuracy-latency trade-off frontier. Next, we explore emerging efficient attention alternatives to evaluate their potential as candidate building operators. Using the identified promising operators, we construct an evolutionary search framework to automatically discover latency-optimal combinations of these operators within hybrid SLMs, thereby advancing the accuracy-latency frontier. In addition to architectural improvements, we further enhance SLM training using a weight normalization technique that enables more effective weight updates and improves final convergence. Combining these methods, we introduce a new family of hybrid SLMs, called Nemotron-Flash, which significantly advances the accuracy-efficiency frontier of state-of-the-art SLMs, e.g., achieving over +5.5% average accuracy, 1.3x/1.9x lower latency, and 18.7x/45.6x higher throughput compared to Qwen3-1.7B/0.6B, respectively.

Learned sparse retrieval (LSR) is a family of first-stage retrieval methods that are trained to generate sparse lexical representations of queries and documents for use with an inverted index. Many LSR methods have been recently introduced, with Splade models achieving state-of-the-art performance on MSMarco. Despite similarities in their model architectures, many LSR methods show substantial differences in effectiveness and efficiency. Differences in the experimental setups and configurations used make it difficult to compare the methods and derive insights. In this work, we analyze existing LSR methods and identify key components to establish an LSR framework that unifies all LSR methods under the same perspective. We then reproduce all prominent methods using a common codebase and re-train them in the same environment, which allows us to quantify how components of the framework affect effectiveness and efficiency. We find that (1) including document term weighting is most important for a method's effectiveness, (2) including query weighting has a small positive impact, and (3) document expansion and query expansion have a cancellation effect. As a result, we show how removing query expansion from a state-of-the-art model can reduce latency significantly while maintaining effectiveness on MSMarco and TripClick benchmarks. Our code is publicly available at https://github.com/thongnt99/learned-sparse-retrieval

RAG (Retrieval Augmented Generation) allows LLMs (large language models) to generate better responses with external knowledge, but using more external knowledge often improves generation quality at the expense of response delay. Prior work either reduces the response delay (through better scheduling of RAG queries) or strives to maximize quality (which involves tuning the RAG workflow), but they fall short in optimizing the tradeoff between the delay and quality of RAG responses. This paper presents RAGServe, the first RAG system that jointly schedules queries and adapts the key RAG configurations of each query, such as the number of retrieved text chunks and synthesis methods, in order to balance quality optimization and response delay reduction. Using 4 popular RAG-QA datasets, we show that compared with the state-of-the-art RAG optimization schemes, RAGServe reduces the generation latency by 1.64-2.54times without sacrificing generation quality.

Test-time scaling (TTS) boosts LLM reasoning via long chain-of-thought (CoT), but the linear KV-cache growth amplifies the memory-bound bottleneck of LLM decoding. Query-aware page-level sparse decoding can achieve state-of-the-art performance under constrained FLOPs budgets, but is limited by both sequential-dependent page filtering and coarse-grained token selection, hampering serving efficiency and model performance on TTS tasks under high concurrency and long CoT scenarios (consuming even higher runtime than the forward pipeline itself). In this paper, we first find that the current-step query state can be accurately approximated in a unified manner from a short window of recent queries, enabling training-free query-aware sparsity without waiting in the decoding loop. We propose AsyncSpade, an asynchronous framework for efficient TTS built on two core components: (1) a novel light-weight temporal-regressive module that predicts the next-token query state; (2) an asynchronous and disaggregated framework that decouples the KV cache filtering from the auto-regressive decoding loop, overlapping the token-level KV selection with the forward inference computation through asynchronism. To our knowledge, AsyncSpade is the first to eliminate the sequential dependence without sacrificing model performance. We validate the effectiveness of AsyncSpade on common LLM serving setups with an A100 node, where AsyncSpade fully overlaps KV-cache operations with the inference pipeline, achieving theoretical optimal time-per-output-token (TPOT). Specifically, AsyncSpade delivers over 20% reduction on TPOT compared to SoTA baseline (i.e. Quest) and at least 50% TPOT reduction compared to full attention on Qwen3-8B and Qwen3-32B models, while matching or surpassing their accuracy on various TTS benchmarks (AIME-24/25, GPQA-Diamond, MATH-500).

The rapid evolution of large language models (LLMs) has unlocked their capabilities in advanced reasoning tasks like mathematical problem-solving, code generation, and legal analysis. Central to this progress are inference-time reasoning algorithms, which refine outputs by exploring multiple solution paths, at the cost of increasing compute demands and response latencies. Existing serving systems fail to adapt to the scaling behaviors of these algorithms or the varying difficulty of queries, leading to inefficient resource use and unmet latency targets. We present Dynasor, a system that optimizes inference-time compute for LLM reasoning queries. Unlike traditional engines, Dynasor tracks and schedules requests within reasoning queries and uses Certaindex, a proxy that measures statistical reasoning progress based on model certainty, to guide compute allocation dynamically. Dynasor co-adapts scheduling with reasoning progress: it allocates more compute to hard queries, reduces compute for simpler ones, and terminates unpromising queries early, balancing accuracy, latency, and cost. On diverse datasets and algorithms, Dynasor reduces compute by up to 50% in batch processing and sustaining 3.3x higher query rates or 4.7x tighter latency SLOs in online serving.

Scaling test-time compute has emerged as a key ingredient for enabling large language models (LLMs) to solve difficult problems, but comes with high latency and inference cost. We introduce sleep-time compute, which allows models to "think" offline about contexts before queries are presented: by anticipating what queries users might ask and pre-computing useful quantities, we can significantly reduce the compute requirements at test-time. To demonstrate the efficacy of our method, we create modified versions of two reasoning tasks - Stateful GSM-Symbolic and Stateful AIME. We find that sleep-time compute can reduce the amount of test-time compute needed to achieve the same accuracy by ~ 5x on Stateful GSM-Symbolic and Stateful AIME and that by scaling sleep-time compute we can further increase accuracy by up to 13% on Stateful GSM-Symbolic and 18% on Stateful AIME. Furthermore, we introduce Multi-Query GSM-Symbolic, which extends GSM-Symbolic by including multiple related queries per context. By amortizing sleep-time compute across related queries about the same context using Multi-Query GSM-Symbolic, we can decrease the average cost per query by 2.5x. We then conduct additional analysis to understand when sleep-time compute is most effective, finding the predictability of the user query to be well correlated with the efficacy of sleep-time compute. Finally, we conduct a case-study of applying sleep-time compute to a realistic agentic SWE task.

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.

Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some dimensions of this progress are illusory: the majority of the popular IR benchmarks today focus exclusively on downstream task accuracy and thus conceal the costs incurred by systems that trade away efficiency for quality. Latency, hardware cost, and other efficiency considerations are paramount to the deployment of IR systems in user-facing settings. We propose that IR benchmarks structure their evaluation methodology to include not only metrics of accuracy, but also efficiency considerations such as a query latency and the corresponding cost budget for a reproducible hardware setting. For the popular IR benchmarks MS MARCO and XOR-TyDi, we show how the best choice of IR system varies according to how these efficiency considerations are chosen and weighed. We hope that future benchmarks will adopt these guidelines toward more holistic IR evaluation.

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.

Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifiable information (PII) in user queries can reach model endpoints before the system determines whether that data should leave its jurisdictional boundary. Serving all queries through a single large model consumes full GPU capacity regardless of query complexity while offering no mechanism for geographic routing. Mixture-of-Experts architectures do not address this routing occurs between expert layers within the model after data has already arrived at the endpoint, with all experts loaded in memory regardless of query complexity. We propose a classifier-gated routing architecture that enforces compliance by design. A trained encoder classifier sits before any decoder inference, evaluating each query for complexity and data sensitivity, then routing it to an appropriately sized dense model in the appropriate geographic location. PII-containing queries route to local endpoints before any LLM computation begins, making data residency violations structurally impossible. Simple queries reach small, fast models at a fraction of the cost. Our evaluation on 600 queries demonstrates 39% median latency reduction, 33-52% cost savings depending on query distribution, and generation throughput of 122-200 tokens/second versus 50-64 for the baseline. The encoder classifier achieves 99.2% accuracy with near-perfect PII recall at 7ms inference overhead, establishing pre-inference classification as a practical path to compliance-by-design LLM deployment.

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster. However existing scheduling algorithms treat LLM workloads as monolithic jobs without considering the distinct characteristics of the two phases in each workload. This leads to sub-optimal scheduling and increased response latency. In this work, we propose a heuristic-guided reinforcement learning-based intelligent router for data-driven and workload-aware scheduling. Our router leverages a trainable response-length predictor, and a novel formulation for estimating the impact of mixing different workloads to schedule queries across LLM instances and achieve over 11\% lower end-to-end latency than existing approaches.

A problem with many current Large Language Model (LLM) driven spoken dialogues is the response time. Some efforts such as Groq address this issue by lightning fast processing of the LLM, but we know from the cognitive psychology literature that in human-to-human dialogue often responses occur prior to the speaker completing their utterance. No amount of delay for LLM processing is acceptable if we wish to maintain human dialogue latencies. In this paper, we discuss methods for understanding an utterance in close to real time and generating a response so that the system can comply with human-level conversational turn delays. This means that the information content of the final part of the speaker's utterance is lost to the LLM. Using the Google NaturalQuestions (NQ) database, our results show GPT-4 can effectively fill in missing context from a dropped word at the end of a question over 60% of the time. We also provide some examples of utterances and the impacts of this information loss on the quality of LLM response in the context of an avatar that is currently under development. These results indicate that a simple classifier could be used to determine whether a question is semantically complete, or requires a filler phrase to allow a response to be generated within human dialogue time constraints.

Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In latency-sensitive applications, rather than waiting for the full utterance, translations should be spoken as soon as the information in the input is present. In this work, we introduce a system for simultaneous S2ST targeting real-world use cases. Our system supports translation from 57 languages to English with tunable parameters for dynamically adjusting the latency of the output -- including four policies for determining when to speak an output sequence. We show that these policies achieve offline-level accuracy with minimal increases in latency over a Greedy (wait-k) baseline. We open-source our evaluation code and interactive test script to aid future SimulS2ST research and application development.

Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own strengths and weaknesses, LLM routing aims to identify the most suitable model for each query in the stream to maximize response quality and minimize cost and latency. However, the challenges involve: (1) dynamic trade-offs among quality, cost, and latency; (2) enabling continual learning in deployed systems; and (3) navigating a varying (e.g., new LLM addition or old LLM removal) set of LLM candidates over time. To bridge these gaps, we develop MixLLM, a dynamic contextual-bandit-based routing system for query-LLM assignment. Specifically, we first leverage query tags to enhance query embeddings for the routing task. Next, we design lightweight prediction models to estimate the response qualities and costs of queries over LLMs. We then devise a meta-decision maker to choose the query-LLM assignments to best tradeoff response quality, cost, and latency. Finally, the system benefits from continual training, allowing it to adapt to evolving queries and user feedback over time. Our extensive experiments show that MixLLM achieves the best trade-offs in response quality, cost, and latency (97.25% of GPT-4's quality at 24.18% of the cost under the time constraint).

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.

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.

Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechanism. The inference consists of prefilling and decoding phases. Although several attempts have been made to accelerate decoding, the inefficiency of the prefilling phase, especially for long-context tasks, remains a challenge. In this paper, we observe a locality in query criticality during the prefilling phase of long-context processing: adjacent query tokens tend to focus on similar subsets of the past Key-Value (KV) cache. Based on this observation, we propose CritiPrefill, a criticality-based segment-wise prefilling method. This method partitions the input sequence's queries and KV cache into segments and blocks, utilizing a segment-wise algorithm to estimate the query criticality. By pruning non-critical computations between query segments and cache blocks in the self-attention mechanism, the prefilling process can be significantly accelerated. Extensive evaluations on multiple long-context datasets show up to 2.7x speedup on Llama3-8B and 3.0x speedup on Yi-9B for 128K context length on a single A100 GPU, with minimal quality degradation.

Although existing 3D perception algorithms have demonstrated significant improvements in performance, their deployment on edge devices continues to encounter critical challenges due to substantial runtime latency. We propose a new benchmark tailored for online evaluation by considering runtime latency. Based on the benchmark, we build a Latency-Aware 3D Streaming Perception (LASP) framework that addresses the latency issue through two primary components: 1) latency-aware history integration, which extends query propagation into a continuous process, ensuring the integration of historical feature regardless of varying latency; 2) latency-aware predictive detection, a module that compensates the detection results with the predicted trajectory and the posterior accessed latency. By incorporating the latency-aware mechanism, our method shows generalization across various latency levels, achieving an online performance that closely aligns with 80\% of its offline evaluation on the Jetson AGX Orin without any acceleration techniques.

Temporal grounding--returning the interval [t_s, t_e] for a natural-language query over a video--is the language interface to long-form video, yet has been studied on short videos; the dynamics of hour-scale natural-language grounding remain underexplored. We take the position that at hour-scale, the binding constraint is search, not recognition: Video-LLMs are bottlenecked not by localizing a nearby event, but--given a natural-language query--by searching for the relevant region of a long video. To test this, we release ExtremeWhenBench, the first open hour-scale grounding benchmark (2,273 queries over 194 videos, mean 75.7 min, max 9 hr) with an open-form query distribution. Every open Video-LLM collapses while a frame-level retrieval baseline outperforms them; a failure taxonomy attributes 85% of failures to search; and a retrieve-then-ground hybrid recovers 6.7x over the monolithic Video-LLM--mirroring retrieve-then-read in open-domain QA.

Efficient scheduling of LLM inference tasks is essential for achieving low latency and high throughput, particularly with the growing use of reasoning-capable LLMs. Traditional strategies like First-Come-First-Serve (FCFS) often suffer from Head-of-Line (HOL) blocking, where long-running tasks delay shorter ones queued behind them. In this paper, we introduce PARS, a prompt-aware LLM task scheduler that improves serving efficiency by approximating shortest-job-first (SJF) scheduling through pairwise ranking with margin ranking loss. PARS focuses on impactful scheduling decisions and is seamlessly integrated into the state-of-the-art LLM serving system vLLM. It effectively predicts response-length-based task ordering, reducing latency with minimal overhead. Extensive experiments across multiple LLMs and real-world inference datasets show that PARS significantly improves performance, including for reasoning workloads. Furthermore, our cross-model evaluations demonstrate that the design generalizes well, enabling effective scheduling even when predictors are trained on different LLMs.

Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure modes, forecasting tools, and domain-specific agents. We evaluate this problem on AssetOpsBench (AOB), an industrial agent benchmark whose plan-execute pipeline exposes repeated overhead from tool discovery, LLM planning, MCP tool execution, and final summarization. Existing LLM caching techniques such as KV-cache reuse and embedding-based semantic caching were designed for chatbot serving and break down when output validity depends on time, asset, or sensor parameters. We propose two complementary optimization layers for AOB plan-execute pipelines: a temporal semantic cache and a set of MCP workflow optimizations combining disk-backed tool-discovery caching and dependency-aware parallel step execution. MCP workflow optimizations corresponded to a 1.67x speedup and reduced median end-to-end latency by about 40.0% while the temporal-cache benchmark achieved a median of 30.6x speedup on cache hits. Beyond the speedup, our results expose a concrete failure mode of pure semantic caching for parameter-rich industrial queries, providing a critical analysis of how caching choices interact with evaluation correctness in MCP-backed agent benchmarks.

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.

Large language model retrievers improve performance on complex queries, but their practical value depends on efficiency, robustness, and reliable confidence signals in addition to accuracy. We reproduce a reasoning-intensive retrieval benchmark (BRIGHT) across 12 tasks and 14 retrievers, and extend evaluation with cold-start indexing cost, query latency distributions and throughput, corpus scaling, robustness to controlled query perturbations, and confidence use (AUROC) for predicting query success. We also quantify reasoning overhead by comparing standard queries to five provided reasoning-augmented variants, measuring accuracy gains relative to added latency. We find that some reasoning-specialized retrievers achieve strong effectiveness while remaining competitive in throughput, whereas several large LLM-based bi-encoders incur substantial latency for modest gains. Reasoning augmentation incurs minimal latency for sub-1B encoders but exhibits diminishing returns for top retrievers and may reduce performance on formal math/code domains. Confidence calibration is consistently weak across model families, indicating that raw retrieval scores are unreliable for downstream routing without additional calibration. We release all code and artifacts for reproducibility.

Large Language Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving instances can improve resource utilization, but directly applying this approach to Prefill/Decode (P/D) disaggregated systems introduces severe load imbalance, as fluctuating request mixes alter the intrinsic P/D ratio. Existing dynamic adjustment techniques cannot keep up with the bursty traffic patterns of online services. We propose a latency-constraint disaggregated architecture, which separates cluster resources into latency-strict and latency-relaxed pools based on task latency requirements. This design enables flexible placement of offline decode tasks, mitigating P/D imbalance while preserving online performance. To fully exploit this flexibility, we propose (1) a bottleneck-based scheduler guided by a Roofline-based performance model for performance bottleneck based scheduling, and (2) a fast preemption mechanism that strictly enforces Service Level Objectives (SLOs) for online requests. Experiments on real-world traces show that compared to existing offline system approaches, our method improves offline throughput by up to 3x, while maintaining online request SLOs.

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.

Scheduling policies in large-scale Automatic Speech Recognition (ASR) serving pipelines play a key role in determining end-to-end (E2E) latency. Yet, widely used serving engines rely on first-come-first-served (FCFS) scheduling, which ignores variability in request duration and leads to head-of-line blocking under workload drift. We show that audio duration is an accurate proxy for job processing time in ASR models such as Whisper, and use this insight to enable duration-aware scheduling. We integrate two classical algorithms, Shortest Job First (SJF) and Highest Response Ratio Next (HRRN), into vLLM and evaluate them under realistic and drifted workloads. On LibriSpeech test-clean, compared to baseline, SJF reduces median E2E latency by up to 73% at high load, but increases 90th-percentile tail latency by up to 97% due to starvation of long requests. HRRN addresses this trade-off: it reduces median E2E latency by up to 28% while bounding tail-latency degradation to at most 24%. These gains persist under workload drift, with no throughput penalty and <0.1\,ms scheduling overhead per request.

This study introduces CUPID, a novel approach to session-based reciprocal recommendation systems designed for a real-time one-on-one social discovery platform. In such platforms, low latency is critical to enhance user experiences. However, conventional session-based approaches struggle with high latency due to the demands of modeling sequential user behavior for each recommendation process. Additionally, given the reciprocal nature of the platform, where users act as items for each other, training recommendation models on large-scale datasets is computationally prohibitive using conventional methods. To address these challenges, CUPID decouples the time-intensive user session modeling from the real-time user matching process to reduce inference time. Furthermore, CUPID employs a two-phase training strategy that separates the training of embedding and prediction layers, significantly reducing the computational burden by decreasing the number of sequential model inferences by several hundredfold. Extensive experiments on large-scale Azar datasets demonstrate CUPID's effectiveness in a real-world production environment. Notably, CUPID reduces response latency by more than 76% compared to non-asynchronous systems, while significantly improving user engagement.

Since a user usually has to issue a sequence of queries and examine multiple documents to resolve a complex information need in a search session, researchers have paid much attention to evaluating search systems at the session level rather than the single-query level. Most existing session-level metrics evaluate each query separately and then aggregate the query-level scores using a session-level weighting function. The assumptions behind these metrics are that all queries in the session should be involved, and their orders are fixed. However, if a search system could make the user satisfied with her first few queries, she may not need any subsequent queries. Besides, in most real-world search scenarios, due to a lack of explicit feedback from real users, we can only leverage some implicit feedback, such as users' clicks, as relevance labels for offline evaluation. Such implicit feedback might be different from the real relevance in a search session as some documents may be omitted in the previous query but identified in the later reformulations. To address the above issues, we make two assumptions about session-based evaluation, which explicitly describe an ideal session-search system and how to enhance click-through data in computing session-level evaluation metrics. Based on our assumptions, we design a session-level metric called Normalized U-Measure (NUM). NUM evaluates a session as a whole and utilizes an ideal session to normalize the result of the actual session. Besides, it infers session-level relevance labels based on implicit feedback. Experiments on two public datasets demonstrate the effectiveness of NUM by comparing it with existing session-based metrics in terms of correlation with user satisfaction and intuitiveness. We also conduct ablation studies to explore whether these assumptions hold.

As scalable inference services become popular, the cold start latency of an inference engine becomes important. Today, vLLM has evolved into the de facto inference engine of choice for many inference workloads. Although popular, due to its complexity and rapid evolution, there has not been a systematic study of its startup latency. With major architectural innovations such as the V1 API and the introduction of torch.compile, this paper presents the first detailed performance characterization of vLLM startup latency. We break down the startup process into six foundational steps and demonstrate that it is predominantly CPU bound. Each step exhibits consistent and interpretable scaling trends with respect to model-level and system-level parameters, enabling fine-grained attribution of latency sources. Building on these insights, we develop a lightweight analytical model that accurately predicts vLLM startup latency for a given hardware configuration, providing actionable guidance for resource planning in large-scale inference environments. All benchmarking datasets, analysis tools, and prediction scripts are open sourced at https://github.com/upb-cn/vllm-startup-profiler.

For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency. Existing methods on hardware-aware NAS collect a large number of samples (e.g., accuracy and latency) from a target device, either builds a lookup table or a latency estimator. However, such approach is impractical in real-world scenarios as there exist numerous devices with different hardware specifications, and collecting samples from such a large number of devices will require prohibitive computational and monetary cost. To overcome such limitations, we propose Hardware-adaptive Efficient Latency Predictor (HELP), which formulates the device-specific latency estimation problem as a meta-learning problem, such that we can estimate the latency of a model's performance for a given task on an unseen device with a few samples. To this end, we introduce novel hardware embeddings to embed any devices considering them as black-box functions that output latencies, and meta-learn the hardware-adaptive latency predictor in a device-dependent manner, using the hardware embeddings. We validate the proposed HELP for its latency estimation performance on unseen platforms, on which it achieves high estimation performance with as few as 10 measurement samples, outperforming all relevant baselines. We also validate end-to-end NAS frameworks using HELP against ones without it, and show that it largely reduces the total time cost of the base NAS method, in latency-constrained settings. Code is available at https://github.com/HayeonLee/HELP.

Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost. While powerful models deliver better results, they come at a high cost, whereas smaller models are more cost-effective but less capable. To address this trade-off, we propose IRT-Router, a multi-LLM routing framework that efficiently routes user queries to the most suitable LLM. Inspired by Item Response Theory (IRT), a psychological measurement methodology, IRT-Router explicitly models the relationship between LLM capabilities and user query attributes. This not only enables accurate prediction of response performance but also provides interpretable insights, such as LLM abilities and query difficulty. Additionally, we design an online query warm-up technique based on semantic similarity, further enhancing the online generalization capability of IRT-Router. Extensive experiments on 20 LLMs and 12 datasets demonstrate that IRT-Router outperforms most baseline methods in terms of effectiveness and interpretability. Its superior performance in cold-start scenarios further confirms the reliability and practicality of IRT-Router in real-world applications. Code is available at https://github.com/Mercidaiha/IRT-Router.

Standard Retrieval-Augmented Generation (RAG) pipelines route every query through retrieval and generation unconditionally, incurring unnecessary computation and propagating low-quality context to the generator. We introduce EverydayGPT, a lightweight conversational QA system built around a Confidence-Gated Routing (CGR) mechanism that formalises the routing decision as a joint policy over retrieval distance and extraction adequacy. The backbone is a 205M-parameter GPT trained from scratch on 10B tokens of FineWeb-Edu. CGR avoids invoking the costly GPT pathway (~5.9s) for 85 percent of queries by resolving them via fast RAG extraction (~45 ms), yielding over 120x latency reduction on the majority of queries while maintaining answer quality. On a 500-question in-domain benchmark, the system achieves F1 = 0.226 +/- 0.004 compared to 0.171 for GPT-only and 0.210 for unconditional RAG. Gains over strong baselines are modest but consistent, while efficiency improvements are substantial (6.3x mean latency reduction). A structured grounding audit finds no unsupported claims in the sampled set, with explicit scope limitations. We position this work as a study of routing strategies under resource constraints rather than a claim of state-of-the-art performance.

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized query and document embeddings; usually, the former has higher quality while the latter benefits from lower latency. Recently, late-interaction models have been proposed to realize more favorable latency-quality tradeoffs, by using a DE structure followed by a lightweight scorer based on query and document token embeddings. However, these lightweight scorers are often hand-crafted, and there is no understanding of their approximation power; further, such scorers require access to individual document token embeddings, which imposes an increased latency and storage burden. In this paper, we propose novel learnable late-interaction models (LITE) that resolve these issues. Theoretically, we prove that LITE is a universal approximator of continuous scoring functions, even for relatively small embedding dimension. Empirically, LITE outperforms previous late-interaction models such as ColBERT on both in-domain and zero-shot re-ranking tasks. For instance, experiments on MS MARCO passage re-ranking show that LITE not only yields a model with better generalization, but also lowers latency and requires 0.25x storage compared to ColBERT.

Query augmentation makes queries more meaningful by appending further information to the queries to find relevant documents. Current studies have proposed Large Language Model (LLM)-based embedders, which learn representation for embedding and generation for query augmentation in a multi-task manner by leveraging the generative capabilities of LLM. During inference, these jointly trained embedders have conducted query augmentation followed by embedding, showing effective results. However, augmenting every query leads to substantial embedding latency and query augmentation can be detrimental to performance for some queries. Also, previous methods have not been explored in multimodal environments. To tackle these problems, we propose M-Solomon, a universal multimodal embedder that can adaptively determine when to augment queries. Our approach first divides the queries of the training datasets into two groups at the dataset level. One includes queries that require augmentation and the other includes queries that do not. Then, we introduces a synthesis process that generates appropriate augmentations for queries that require them by leveraging a powerful Multimodal LLM (MLLM). Next, we present adaptive query augmentation. Through this step, M-Solomon can conduct query augmentation only when necessary by learning to generate synthetic augmentations with the prefix /augment for queries that demand them and to generate the simple string /embed for others. Experimental results showed that M-Solomon not only surpassed the baseline without augmentation by a large margin but also outperformed the baseline that always used augmentation, providing much faster embedding latency.

We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are complemented and integrated with 253 hand-crafted lexical features extracted from the same corpus. Blending of the relevance signals from the two different groups of features is learned by a classical Learning-to-Rank (LTR) model based on a forest of decision trees. To evaluate our solution, we employ a pipelined architecture where a dense neural retriever serves as the first stage and performs a nearest-neighbor search over the neural representations of the documents. Our LTR model acts instead as the second stage that re-ranks the set of candidates retrieved by the first stage to enhance effectiveness. The results of reproducible experiments conducted with state-of-the-art dense retrievers on publicly available resources show that the proposed solution significantly enhances the end-to-end ranking performance while relatively minimally impacting efficiency. Specifically, we achieve a boost in nDCG@10 of up to 11% with an increase in average query latency of only 4.3%. This confirms the advantage of seamlessly combining two distinct families of signals that mutually contribute to retrieval effectiveness.

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%.

Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all dimensions, it is very difficult to manually balance these trade-offs when there are so many architectural possibilities to consider. In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Unlike previous work, where latency is considered via another, often inaccurate proxy (e.g., FLOPS), our approach directly measures real-world inference latency by executing the model on mobile phones. To further strike the right balance between flexibility and search space size, we propose a novel factorized hierarchical search space that encourages layer diversity throughout the network. Experimental results show that our approach consistently outperforms state-of-the-art mobile CNN models across multiple vision tasks. On the ImageNet classification task, our MnasNet achieves 75.2% top-1 accuracy with 78ms latency on a Pixel phone, which is 1.8x faster than MobileNetV2 [29] with 0.5% higher accuracy and 2.3x faster than NASNet [36] with 1.2% higher accuracy. Our MnasNet also achieves better mAP quality than MobileNets for COCO object detection. Code is at https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet

Modern semantic search and retrieval-augmented generation (RAG) systems rely predominantly on in-memory approximate nearest neighbor (ANN) indexes over high-precision floating-point vectors, resulting in escalating operational cost and inherent trade-offs between latency, throughput, and retrieval accuracy. This paper analyzes the architectural limitations of the dominant "HNSW + float32 + cosine similarity" stack and evaluates existing cost-reduction strategies, including storage disaggregation and lossy vector quantization, which inevitably sacrifice either performance or accuracy. We introduce and empirically evaluate an alternative information-theoretic architecture based on maximally informative binarization (MIB), efficient bitwise distance metrics, and an information-theoretic scoring (ITS) mechanism. Unlike conventional ANN systems, this approach enables exhaustive search over compact binary representations, allowing deterministic retrieval and eliminating accuracy degradation under high query concurrency. Using the MAIR benchmark across 14 datasets and 10,038 queries, we compare this architecture against Elasticsearch, Pinecone, PGVector, and Qdrant. Results demonstrate retrieval quality comparable to full-precision systems, while achieving substantially lower latency and maintaining constant throughput at high request rates. We show that this architectural shift enables a truly serverless, cost-per-query deployment model, challenging the necessity of large in-memory ANN indexes for high-quality semantic search.

Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond these shallow signals, recent benchmarks introduce reasoning-heavy queries; however, they primarily shift the burden to query-side processing techniques -- like prompting or multi-hop retrieval -- that can help resolve complexity. In contrast, we present ImpliRet, a benchmark that shifts the reasoning challenge to document-side processing: The queries are simple, but relevance depends on facts stated implicitly in documents through temporal (e.g., resolving "two days ago"), arithmetic, and world knowledge relationships. We evaluate a range of sparse and dense retrievers, all of which struggle in this setting: the best nDCG@10 is only 15.07%. We also test whether long-context models can overcome this limitation. But even with a short context of only ten documents, including the positive document, GPT-4.1 scores only 35.06%, showing that document-side reasoning remains a challenge. Our codes are available at github.com/ZeinabTaghavi/IMPLIRET.Contribution.

The Needle-in-a-Haystack (NIAH) benchmark is widely used to evaluate Large Language Models' (LLMs) ability to understand long contexts (LC). It evaluates the capability to identify query-relevant context within extensive query-irrelevant passages. Although this method serves as a widely accepted standard for evaluating long-context understanding, our findings suggest it may overestimate the true LC capability of LLMs. We demonstrate that even state-of-the-art models such as GPT-4o struggle to intactly incorporate given contexts made up of solely query-relevant ten sentences. In response, we introduce a novel benchmark, NeedleChain, where the context consists entirely of query-relevant information, requiring the LLM to fully grasp the input to answer correctly. Our benchmark allows for flexible context length and reasoning order, offering a more comprehensive analysis of LLM performance. Additionally, we propose an extremely simple yet compelling strategy to improve LC understanding capability of LLM: ROPE Contraction. Our experiments with various advanced LLMs reveal a notable disparity between their ability to process large contexts and their capacity to fully understand them. Source code and datasets are available at https://github.com/hyeonseokk/NeedleChain

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute increase. Prompt compression, which reduces the size of input prompts while aiming to preserve performance on downstream tasks, has established itself as a cost-effective and low-latency method for accelerating inference in large language models. However, its usefulness depends on whether the additional preprocessing time during generation is offset by faster decoding. We present the first systematic, large-scale study of this trade-off, with thousands of runs and 30,000 queries across several open-source LLMs and three GPU classes. Our evaluation separates compression overhead from decoding latency while tracking output quality and memory usage. LLMLingua achieves up to 18% end-to-end speed-ups, when prompt length, compression ratio, and hardware capacity are well matched, with response quality remaining statistically unchanged across summarization, code generation, and question answering tasks. Outside this operating window, however, the compression step dominates and cancels out the gains. We also show that effective compression can reduce memory usage enough to offload workloads from data center GPUs to commodity cards, with only a 0.3s increase in latency. Our open-source profiler predicts the latency break-even point for each model-hardware setup, providing practical guidance on when prompt compression delivers real-world benefits.

Large language models achieve high task performance yet often hallucinate or rely on outdated knowledge. Retrieval-augmented generation (RAG) addresses these gaps by coupling generation with external search. We analyse how hyperparameters influence speed and quality in RAG systems, covering Chroma and Faiss vector stores, chunking policies, cross-encoder re-ranking, and temperature, and we evaluate six metrics: faithfulness, answer correctness, answer relevancy, context precision, context recall, and answer similarity. Chroma processes queries 13% faster, whereas Faiss yields higher retrieval precision, revealing a clear speed-accuracy trade-off. Naive fixed-length chunking with small windows and minimal overlap outperforms semantic segmentation while remaining the quickest option. Re-ranking provides modest gains in retrieval quality yet increases runtime by roughly a factor of 5, so its usefulness depends on latency constraints. These results help practitioners balance computational cost and accuracy when tuning RAG systems for transparent, up-to-date responses. Finally, we re-evaluate the top configurations with a corrective RAG workflow and show that their advantages persist when the model can iteratively request additional evidence. We obtain a near-perfect context precision (99%), which demonstrates that RAG systems can achieve extremely high retrieval accuracy with the right combination of hyperparameters, with significant implications for applications where retrieval quality directly impacts downstream task performance, such as clinical decision support in healthcare.

Recent advances in leveraging the agentic paradigm of large language models (LLMs) utilization have significantly enhanced Text-to-SQL capabilities, enabling users without specialized database expertise to query data intuitively. However, deploying these agentic LLM-based Text-to-SQL systems in production poses substantial challenges due to their inherently multi-stage workflows, stringent latency constraints, and potentially heterogeneous GPU infrastructure in enterprise environments. Current LLM serving frameworks lack effective mechanisms for handling interdependent inference tasks, dynamic latency variability, and resource heterogeneity, leading to suboptimal performance and frequent service-level objective (SLO) violations. In this paper, we introduce HEXGEN-TEXT2SQL, a novel framework designed explicitly to schedule and execute agentic multi-stage LLM-based Text-to-SQL workflows on heterogeneous GPU clusters that handle multi-tenant end-to-end queries. HEXGEN-TEXT2SQL introduce a hierarchical scheduling approach combining global workload-balanced task dispatching and local adaptive urgency-guided prioritization, guided by a systematic analysis of agentic Text-to-SQL workflows. Additionally, we propose a lightweight simulation-based method for tuning critical scheduling hyperparameters, further enhancing robustness and adaptability. Our extensive evaluation on realistic Text-to-SQL benchmarks demonstrates that HEXGEN-TEXT2SQL significantly outperforms state-of-the-art LLM serving frameworks. Specifically, HEXGEN-TEXT2SQL reduces latency deadlines by up to 1.67times (average: 1.41times) and improves system throughput by up to 1.75times (average: 1.65times) compared to vLLM under diverse, realistic workload conditions. Our code is available at https://github.com/Relaxed-System-Lab/Hexgen-Flow.

Building effective dense retrieval systems remains difficult when relevance supervision is not available. Recent work has looked to overcome this challenge by using a Large Language Model (LLM) to generate hypothetical documents that can be used to find the closest real document. However, this approach relies solely on the LLM to have domain-specific knowledge relevant to the query, which may not be practical. Furthermore, generating hypothetical documents can be inefficient as it requires the LLM to generate a large number of tokens for each query. To address these challenges, we introduce Real Document Embeddings from Relevance Feedback (ReDE-RF). Inspired by relevance feedback, ReDE-RF proposes to re-frame hypothetical document generation as a relevance estimation task, using an LLM to select which documents should be used for nearest neighbor search. Through this re-framing, the LLM no longer needs domain-specific knowledge but only needs to judge what is relevant. Additionally, relevance estimation only requires the LLM to output a single token, thereby improving search latency. Our experiments show that ReDE-RF consistently surpasses state-of-the-art zero-shot dense retrieval methods across a wide range of low-resource retrieval datasets while also making significant improvements in latency per-query.

Query rewriting is a classical technique for transforming complex declarative SQL queries into ``lean'' equivalents that are conducive to (a) faster execution from a performance perspective, and (b) better understanding from a developer perspective. The rewriting is typically achieved via transformation rules, but these rules are limited in scope and difficult to update in a production system. In recent times, LLM-based techniques have also been mooted, but they are prone to both semantic and syntactic errors. We investigate here, how the remarkable cognitive capabilities of LLMs can be leveraged for performant query rewriting while incorporating safeguards and optimizations to ensure correctness and efficiency. Our study shows that these goals can be progressively achieved through incorporation of (a) an ensemble suite of basic prompts, (b) database-sensitive prompts via redundancy removal and selectivity-based rewriting rules, and (c) LLM token probability-guided rewrite paths. Further, a suite of statistical and logic-based tools can be used to guard against errors produced by the model. We have implemented the above LLM-infused techniques in the LITHE system, and evaluated complex analytic queries from multiple benchmarks on contemporary database platforms. The results show significant improvements over SOTA rewriting techniques -- for instance, on TPC-DS, LITHE constructed productive (>1.5x speedup) rewrites for two-thirds of the query suite, delivering four times more coverage than SOTA. Further, the geometric mean of its estimated execution speedups was an order-of-magnitude jump over SOTA performance. In essence, LITHE offers a potent and robust LLM-based intermediary between enterprise applications and database engines.

Multimodal language models that process both text and speech have a potential for applications in spoken dialogue systems. However, current models face two major challenges in response generation latency: (1) generating a spoken response requires the prior generation of a written response, and (2) speech sequences are significantly longer than text sequences. This study addresses these issues by extending the input and output sequences of the language model to support the parallel generation of text and speech. Our experiments on spoken question answering tasks demonstrate that our approach improves latency while maintaining the quality of response content. Additionally, we show that latency can be further reduced by generating speech in multiple sequences. Demo samples are available at https://rinnakk.github.io/research/publications/PSLM.

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive requests emphasizing per-token latency in streaming chat, deadline-sensitive requests requiring rapid full responses to trigger external tools, and compound requests with evolving dependencies across multiple LLM calls. Despite-or perhaps, because of-this workload diversity and unpredictable request information (e.g., response lengths and dependencies), existing request schedulers have focused on aggregate performance, unable to ensure application-level SLO needs. This paper presents JITServe, the first SLO-aware LLM serving system designed to maximize service goodput (e.g., the number of tokens meeting request SLOs) across diverse workloads. JITServe novelly schedules requests using imprecise request information and gradually relaxes this conservatism by refining request information estimates as generation progresses. It applies a grouped margin goodput maximization algorithm to allocate just enough serving bandwidth to satisfy each request's SLO just-in-time (JIT), maximizing residual capacity for others, while deciding the composition of requests in a batch to maximize efficiency and goodput with provable guarantees. Our evaluation across diverse realistic workloads, including chat, deep research, and agentic pipelines, shows that JITServe improves service goodput by 1.4x-6.3x, alternatively achieving 28.5%-83.2% resource savings, compared to state-of-the-art designs.

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt templates, and documents provided for context. Our key insight is that by precomputing and storing the attention states of these frequently occurring text segments on the inference server, we can efficiently reuse them when these segments appear in user prompts. Prompt Cache employs a schema to explicitly define such reusable text segments, called prompt modules. The schema ensures positional accuracy during attention state reuse and provides users with an interface to access cached states in their prompt. Using a prototype implementation, we evaluate Prompt Cache across several LLMs. We show that Prompt Cache significantly reduce latency in time-to-first-token, especially for longer prompts such as document-based question answering and recommendations. The improvements range from 8x for GPU-based inference to 60x for CPU-based inference, all while maintaining output accuracy and without the need for model parameter modifications.

Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples. In this work, we show how to efficiently establish, at test-time, a solid tradeoff between robustness and accuracy when mitigating query-based attacks. Given that these attacks necessarily explore low-confidence regions, our insight is that activating dedicated defenses, such as random noise defense and random image transformations, only for low-confidence inputs is sufficient to prevent them. Our approach is independent of training and supported by theory. We verify the effectiveness of our approach for various existing defenses by conducting extensive experiments on CIFAR-10, CIFAR-100, and ImageNet. Our results confirm that our proposal can indeed enhance these defenses by providing better tradeoffs between robustness and accuracy when compared to state-of-the-art approaches while being completely training-free.

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across all users and requests. We find that this strategy not only leads to strong prefill-decoding interferences but also couples the resource allocation and parallelism plans for both phases. LLM applications often emphasize individual latency for each phase: time to first token (TTFT) for the prefill phase and time per output token (TPOT) of each request for the decoding phase. In the presence of stringent latency requirements, existing systems have to prioritize one latency over the other, or over-provision compute resources to meet both. DistServe assigns prefill and decoding computation to different GPUs, hence eliminating prefill-decoding interferences. Given the application's TTFT and TPOT requirements, DistServe co-optimizes the resource allocation and parallelism strategy tailored for each phase. DistServe also places the two phases according to the serving cluster's bandwidth to minimize the communication caused by disaggregation. As a result, DistServe significantly improves LLM serving performance in terms of the maximum rate that can be served within both TTFT and TPOT constraints on each GPU. Our evaluations show that on various popular LLMs, applications, and latency requirements, DistServe can serve 4.48x more requests or 10.2x tighter SLO, compared to state-of-the-art systems, while staying within latency constraints for > 90% of requests.

Adaptive retrieval-augmented generation (ARAG) aims to dynamically determine the necessity of retrieval for queries instead of retrieving indiscriminately to enhance the efficiency and relevance of the sourced information. However, previous works largely overlook the evaluation of ARAG approaches, leading to their effectiveness being understudied. This work presents a benchmark, RetrievalQA, comprising 1,271 short-form questions covering new world and long-tail knowledge. The knowledge necessary to answer the questions is absent from LLMs; therefore, external information must be retrieved to answer correctly. This makes RetrievalQA a suitable testbed to evaluate existing ARAG methods. We observe that calibration-based methods heavily rely on threshold tuning, while vanilla prompting is inadequate for guiding LLMs to make reliable retrieval decisions. Based on our findings, we propose Time-Aware Adaptive Retrieval (TA-ARE), a simple yet effective method that helps LLMs assess the necessity of retrieval without calibration or additional training. The dataset and code will be available at https://github.com/hyintell/RetrievalQA

Serving large language models (LLMs) in production can incur substantial costs, which has prompted recent advances in inference system optimizations. Today, these systems are evaluated against conventional latency and throughput metrics (eg. TTFT, TBT, Normalised Latency and TPOT). However, these metrics fail to fully capture the nuances of LLM inference, leading to an incomplete assessment of user-facing performance crucial for real-time applications such as chat and translation. In this paper, we first identify the pitfalls of current performance metrics in evaluating LLM inference systems. We then propose Etalon, a comprehensive performance evaluation framework that includes fluidity-index -- a novel metric designed to reflect the intricacies of the LLM inference process and its impact on real-time user experience. Finally, we evaluate various existing open-source platforms and model-as-a-service offerings using Etalon, discussing their strengths and weaknesses. Etalon is available at https://github.com/project-etalon/etalon.

Pre-trained language models are increasingly important components across multiple information retrieval (IR) paradigms. Late interaction, introduced with the ColBERT model and recently refined in ColBERTv2, is a popular paradigm that holds state-of-the-art status across many benchmarks. To dramatically speed up the search latency of late interaction, we introduce the Performance-optimized Late Interaction Driver (PLAID). Without impacting quality, PLAID swiftly eliminates low-scoring passages using a novel centroid interaction mechanism that treats every passage as a lightweight bag of centroids. PLAID uses centroid interaction as well as centroid pruning, a mechanism for sparsifying the bag of centroids, within a highly-optimized engine to reduce late interaction search latency by up to 7times on a GPU and 45times on a CPU against vanilla ColBERTv2, while continuing to deliver state-of-the-art retrieval quality. This allows the PLAID engine with ColBERTv2 to achieve latency of tens of milliseconds on a GPU and tens or just few hundreds of milliseconds on a CPU at large scale, even at the largest scales we evaluate with 140M passages.

Query rewriting refers to an established family of approaches that are applied to underspecified and ambiguous queries to overcome the vocabulary mismatch problem in document ranking. Queries are typically rewritten during query processing time for better query modelling for the downstream ranker. With the advent of large-language models (LLMs), there have been initial investigations into using generative approaches to generate pseudo documents to tackle this inherent vocabulary gap. In this work, we analyze the utility of LLMs for improved query rewriting for text ranking tasks. We find that there are two inherent limitations of using LLMs as query re-writers -- concept drift when using only queries as prompts and large inference costs during query processing. We adopt a simple, yet surprisingly effective, approach called context aware query rewriting (CAR) to leverage the benefits of LLMs for query understanding. Firstly, we rewrite ambiguous training queries by context-aware prompting of LLMs, where we use only relevant documents as context.Unlike existing approaches, we use LLM-based query rewriting only during the training phase. Eventually, a ranker is fine-tuned on the rewritten queries instead of the original queries during training. In our extensive experiments, we find that fine-tuning a ranker using re-written queries offers a significant improvement of up to 33% on the passage ranking task and up to 28% on the document ranking task when compared to the baseline performance of using original queries.

Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a subset of dimensions is consistently helpful for ranking. Prior work addresses this via pseudo-relevance feedback (PRF) based dimension importance estimation, which can produce query-aware masks without labeled data but often relies on noisy pseudo signals and heuristic test-time procedures. In contrast, supervised adapter methods leverage relevance labels to improve embedding quality, yet they learn global transformations shared across queries and do not explicitly model query-aware dimension importance. We propose a Query-Aware Adaptive Dimension Selection framework that learns to predict per-dimension importance directly from query embedding. We first construct oracle dimension importance distributions over embedding dimensions using supervised relevance labels, and then train a predictor to map a query embedding to these label-distilled importance scores. At inference, the predictor selects a query-aware subset of dimensions for similarity computation based solely on the query embedding, without pseudo-relevance feedback. Experiments across multiple dense retrievers and benchmarks show that our learned dimension selector improves retrieval effectiveness over the full-dimensional baseline as well as PRF-based masking and supervised adapter baselines.

Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text. Existing retrieval-augmented generation (RAG) systems are optimized primarily for semantic relevance, but retrieving plausible passages does not guarantee correct query execution. We introduce QO-Bench, a diagnostic benchmark for query-operator question answering over typed event tuples. The benchmark covers 22,984 news articles and 614 corporate events across 18 query templates, evaluated on 785 questions. Each gold answer is deterministically computed from typed event tuples and scored by recall, with answers matched to the gold tuples by exact match rather than an LLM judge. This design enables operator-level diagnosis such as joins and intersection. We evaluate RAG, ReAct RAG, GraphRAG, and information-extraction-to-SQL under matched conditions, with a long-context oracle ceiling to isolate retrieval failure. A two-axis framework -- index-time preservation versus query-time execution -- predicts where each paradigm fails, and the results bear it out: systems retrieve relevant text but discard the typed values operators need, and the deployable paradigm ranking inverts across operators, with similarity retrieval leading on filter/project and extraction-to-SQL on intersection and counting. Even given the gold evidence, a long-context oracle stays far from saturated, so operator execution -- not retrieval alone -- is a core bottleneck that a stronger answer model does not remove. QO-Bench reframes the goal from passage relevance to query-operator-preserving retrieval.

This paper introduces UnSeenTimeQA, a novel time-sensitive question-answering (TSQA) benchmark that diverges from traditional TSQA benchmarks by avoiding factual and web-searchable queries. We present a series of time-sensitive event scenarios decoupled from real-world factual information. It requires large language models (LLMs) to engage in genuine temporal reasoning, disassociating from the knowledge acquired during the pre-training phase. Our evaluation of six open-source LLMs (ranging from 2B to 70B in size) and three closed-source LLMs reveal that the questions from the UnSeenTimeQA present substantial challenges. This indicates the models' difficulties in handling complex temporal reasoning scenarios. Additionally, we present several analyses shedding light on the models' performance in answering time-sensitive questions.

Query rewriting plays a vital role in enhancing conversational search by transforming context-dependent user queries into standalone forms. Existing approaches primarily leverage human-rewritten queries as labels to train query rewriting models. However, human rewrites may lack sufficient information for optimal retrieval performance. To overcome this limitation, we propose utilizing large language models (LLMs) as query rewriters, enabling the generation of informative query rewrites through well-designed instructions. We define four essential properties for well-formed rewrites and incorporate all of them into the instruction. In addition, we introduce the role of rewrite editors for LLMs when initial query rewrites are available, forming a "rewrite-then-edit" process. Furthermore, we propose distilling the rewriting capabilities of LLMs into smaller models to reduce rewriting latency. Our experimental evaluation on the QReCC dataset demonstrates that informative query rewrites can yield substantially improved retrieval performance compared to human rewrites, especially with sparse retrievers.

The rapid expansion of digital information and knowledge across structured and unstructured sources has heightened the importance of Information Retrieval (IR). While dense retrieval methods have substantially improved semantic matching for general queries, they consistently underperform on queries with explicit temporal constraints--often those containing numerical expressions and time specifiers such as ``in 2015.'' Existing approaches to Temporal Information Retrieval (TIR) improve temporal reasoning but often suffer from catastrophic forgetting, leading to reduced performance on non-temporal queries. To address this, we propose Time-Specifier Model Merging (TSM), a novel method that enhances temporal retrieval while preserving accuracy on non-temporal queries. TSM trains specialized retrievers for individual time specifiers and merges them in to a unified model, enabling precise handling of temporal constraints without compromising non-temporal retrieval. Extensive experiments on both temporal and non-temporal datasets demonstrate that TSM significantly improves performance on temporally constrained queries while maintaining strong results on non-temporal queries, consistently outperforming other baseline methods. Our code is available at https://github.com/seungyoonee/TSM .

We propose the concept of Intra-Query Runtime Elasticity (IQRE) for cloud-native data analysis. IQRE enables a cloud-native OLAP engine to dynamically adjust a query's Degree of Parallelism (DOP) during execution. This capability allows users to utilize cloud computing resources more cost-effectively. We present Accordion, the first IQRE query engine. Accordion can adjust the parallelism of a query at any point during query execution without pausing data processing. It features a user-friendly interface and an auto-tuner backed by a "what-if" service to allow users to adjust the DOP according to their query latency constraints. The design of Accordion follows the execution model in Presto, an open-source distributed SQL query engine developed at Meta. We present the implementation of Accordion and demonstrate its ease of use, showcasing how it enables users to minimize compute resource consumption while meeting their query time constraints.

Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations often overlook the temporal dimension of tool use, especially the impact of tool response latency, and are usually limited to single-task settings. In real-world applications, multiple tasks often need to be executed concurrently, and overall efficiency depends on whether an agent can use idle time while waiting for tool responses. We refer to this capability as asynchronous tool calling. To evaluate it, we propose AsyncTool, a benchmark for assessing LLM-based agents in interactive multi-task tool-use environments with delayed tool feedback. AsyncTool presents multiple heterogeneous tasks simultaneously and simulates realistic tool response latency during execution. Using a hybrid data evolution strategy, we construct a diverse asynchronous multitasking dataset that covers multiple scenarios and tool-use patterns. We evaluate models at the step, sub-task, and task levels, and introduce efficiency-oriented metrics to measure task coordination and completion efficiency. Extensive experiments show that delayed tool feedback poses substantial challenges to current agents and leads to clear performance degradation. Models that better coordinate task switching, dependency tracking, and state maintenance achieve stronger performance on AsyncTool. Our analysis identifies key failure modes of current tool-using agents and provides practical insights for designing future systems with stronger temporal reasoning and coordination capabilities.

Dense retrieval has made significant advancements in information retrieval (IR) by achieving high levels of effectiveness while maintaining online efficiency during a single-pass retrieval process. However, the application of pseudo relevance feedback (PRF) to further enhance retrieval effectiveness results in a doubling of online latency. To address this challenge, this paper presents a single-pass dense retrieval framework that shifts the PRF process offline through the utilization of pre-generated pseudo-queries. As a result, online retrieval is reduced to a single matching with the pseudo-queries, hence providing faster online retrieval. The effectiveness of the proposed approach is evaluated on the standard TREC DL and HARD datasets, and the results demonstrate its promise. Our code is openly available at https://github.com/Rosenberg37/OPRF.

We revisit the I/O complexity of attention in large language models. Given query-key-value matrices Q,K,VinR^{ntimes d}, and a machine with fast memory size M, the goal is to compute the "attention matrix" A=softmax(Q K ^{top}/d) V with the minimal number of data transfers between fast and slow memory. Existing methods in the literature, most notably FlashAttention and its variants, incur an I/O cost that depends quadratically on n, while a trivial lower bound only requires Ω(nd) I/O's to read the inputs and write the output. In this work, we present a technique for computing attention where the I/O cost only depends almost-linearly on n in most parameter regimes. This is achieved by developing I/O-efficient algorithms inspired by the recent approximate attention framework of Alman and Song. We also prove corresponding lower bounds in each parameter regime to show that our algorithms are indeed close to I/O-optimal.

Simultaneous speech-to-text translation (SimulST) systems have to balance translation quality with latency--the delay between speech input and the translated output. While quality evaluation is well established, accurate latency measurement remains a challenge. Existing metrics often produce inconsistent or misleading results, especially in the widely used short-form setting, where speech is artificially presegmented. In this paper, we present the first comprehensive analysis of SimulST latency metrics across language pairs, systems, and both short- and long-form regimes. We uncover a structural bias in current metrics related to segmentation that undermines fair and meaningful comparisons. To address this, we introduce YAAL (Yet Another Average Lagging), a refined latency metric that delivers more accurate evaluations in the short-form regime. We extend YAAL to LongYAAL for unsegmented audio and propose SoftSegmenter, a novel resegmentation tool based on word-level alignment. Our experiments show that YAAL and LongYAAL outperform popular latency metrics, while SoftSegmenter enhances alignment quality in long-form evaluation, together enabling more reliable assessments of SimulST systems.

Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm. Meanwhile, despite the rapid advancement of Search Agents, their practical deployment is constrained by a fundamental limitation, termed as 1) Latency Challenge: the serial execution of multi-round reasoning, tool calling, and tool response waiting under the ReAct agent paradigm induces severe end-to-end latency. Intuitively, dLLMs can leverage their distinctive strengths to optimize the operational efficiency of agents under the ReAct agent paradigm. Practically, existing dLLM backbones face the 2) Agent Ability Challenge. That is, existing dLLMs exhibit remarkably weak reasoning and tool-calling capabilities, preventing these advantages from being effectively realized in practice. In this paper, we propose DLLM-Searcher, an optimization framework for dLLM-based Search Agents. To solve the Agent Ability Challenge, we design a two-stage post-training pipeline encompassing Agentic Supervised Fine-Tuning (Agentic SFT) and Agentic Variance-Reduced Preference Optimization Agentic VRPO, which enhances the backbone dLLM's information seeking and reasoning capabilities. To mitigate the Latency Challenge, we leverage the flexible generation mechanism of dLLMs and propose a novel agent paradigm termed Parallel-Reasoning and Acting P-ReAct. P-ReAct guides the model to prioritize decoding tool_call instructions, thereby allowing the model to keep thinking while waiting for the tool's return. Experimental results demonstrate that DLLM-Searcher achieves performance comparable to mainstream LLM-based search agents and P-ReAct delivers approximately 15% inference acceleration. Our code is available at https://anonymous.4open.science/r/DLLM-Searcher-553C

We present **vstash**, a local-first document memory system that combines vector similarity search with full-text keyword matching via Reciprocal Rank Fusion (RRF) and adaptive per-query IDF weighting. All data resides in a single SQLite file using sqlite-vec for approximate nearest neighbor search and FTS5 for keyword matching. We make four primary contributions. **(1)** Self-supervised embedding refinement via hybrid retrieval disagreement: across 753 BEIR queries on SciFact, NFCorpus, and FiQA, 74.5% produce top-10 disagreement between vector-heavy (vec=0.95, fts=0.05) and FTS-heavy (vec=0.05, fts=0.95) search (per-dataset rates 63.4% / 73.4% / 86.7%, Section 5.2), providing a free training signal without human labels. Fine-tuning BGE-small (33M params) with MultipleNegativesRankingLoss on 76K disagreement triples improves NDCG@10 on all 5 BEIR datasets (up to +19.5% on NFCorpus vs. BGE-small base RRF, Table 6). On 3 of 5 datasets, under different preprocessing, the tuned 33M-parameter pipeline matches or exceeds published ColBERTv2 results (110M params) and an untrained BGE-base (110M); on FiQA and ArguAna it underperforms ColBERTv2 (Section 5.5). **(2)** Adaptive RRF with per-query IDF weighting improves NDCG@10 on all 5 BEIR datasets versus fixed weights (up to +21.4% on ArguAna), achieving 0.7263 on SciFact with BGE-small. **(3)** A negative result on post-RRF scoring: frequency+decay, history-augmented recall, and cross-encoder reranking all failed to improve NDCG. **(4)** A production-grade substrate with integrity checking, schema versioning, ranking diagnostics, and a distance-based relevance signal validated on 50,425 relevance-judged queries across the 5 BEIR datasets. Search latency remains 20.9 ms median at 50K chunks with stable NDCG. The fine-tuned model is published as `Stffens/bge-small-rrf-v2` on HuggingFace. All code, data, and experiments are open-source.

Long-horizon agents often compress interaction histories into write-time summaries. This creates a fundamental write-before-query barrier: compression decisions are made before the system knows what a future query will hinge on. As a result, summaries can cause unverifiable omissions -- decisive constraints (e.g., allergies) may be dropped, leaving the agent unable to justify an answer with traceable evidence. Retaining raw logs restores an authoritative source of truth, but grounding on raw logs by default is expensive: many queries are answerable from summaries, yet raw grounding still requires processing far longer contexts, inflating token consumption and latency. We propose TierMem, a provenance-linked framework that casts retrieval as an inference-time evidence allocation problem. TierMem uses a two-tier memory hierarchy to answer with the cheapest sufficient evidence: it queries a fast summary index by default, and a runtime sufficiency router Escalates to an immutable raw-log store only when summary evidence is insufficient. TierMem then writes back verified findings as new summary units linked to their raw sources. On LoCoMo, TierMem achieves 0.851 accuracy (vs.0.873 raw-only) while reducing input tokens by 54.1\% and latency by 60.7%.

Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 and HotpotQA mainly study ``known unknowns'' with clear indications of both what information is missing, and how to find it to answer the question. Hence, good performance on these benchmarks provides a false sense of security. A yet unmet need of the NLP community is a bank of non-factoid, multi-perspective questions involving a great deal of unclear information needs, i.e. ``unknown uknowns''. We claim we can find such questions in search engine logs, which is surprising because most question-intent queries are indeed factoid. We present Researchy Questions, a dataset of search engine queries tediously filtered to be non-factoid, ``decompositional'' and multi-perspective. We show that users spend a lot of ``effort'' on these questions in terms of signals like clicks and session length, and that they are also challenging for GPT-4. We also show that ``slow thinking'' answering techniques, like decomposition into sub-questions shows benefit over answering directly. We release sim 100k Researchy Questions, along with the Clueweb22 URLs that were clicked.

Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limiting their scalability and usability in time-sensitive scenarios. Most existing approaches primarily optimize task performance and inference cost, and explicitly or implicitly assume sequential execution, making them less optimal for controlling latency under parallel execution. In this work, we investigate learning-based orchestration of multi-agent systems with explicit latency supervision under parallel execution. We propose Latency-Aware Multi-agent System (LAMaS), a latency-aware multi-agent orchestration framework that enables parallel execution and explicitly optimizes the critical execution path, allowing the controller to construct execution topology graphs with lower latency under parallel execution. Our experiments show that our approach reduces critical path length by 38-46% compared to the state-of-the-art baseline for multi-agent architecture search across multiple benchmarks, while maintaining or even improving task performance. These results highlight the importance of explicitly optimizing latency under parallel execution when designing efficient multi-agent systems. The code is available at https://github.com/xishi404/LAMaS

The overwhelming volume of data generated and indexed by search engines poses a significant challenge in retrieving documents from the index efficiently and effectively. Even with a well-crafted query, several relevant documents often get buried among a multitude of competing documents, resulting in reduced accessibility or `findability' of the desired document. Consequently, it is crucial to develop a robust methodology for assessing this dimension of Information Retrieval (IR) system performance. While previous studies have focused on measuring document accessibility disregarding user queries and document relevance, there exists no metric to quantify the findability of a document within a given IR system without resorting to manual labor. This paper aims to address this gap by defining and deriving a metric to evaluate the findability of documents as perceived by end-users. Through experiments, we demonstrate the varying impact of different retrieval models and collections on the findability of documents. Furthermore, we establish the findability measure as an independent metric distinct from retrievability, an accessibility measure introduced in prior literature.

Many information retrieval tasks require large labeled datasets for fine-tuning. However, such datasets are often unavailable, and their utility for real-world applications can diminish quickly due to domain shifts. To address this challenge, we develop and motivate a method for using large language models (LLMs) to generate large numbers of synthetic queries cheaply. The method begins by generating a small number of synthetic queries using an expensive LLM. After that, a much less expensive one is used to create large numbers of synthetic queries, which are used to fine-tune a family of reranker models. These rerankers are then distilled into a single efficient retriever for use in the target domain. We show that this technique boosts zero-shot accuracy in long-tail domains, even where only 2K synthetic queries are used for fine-tuning, and that it achieves substantially lower latency than standard reranking methods. We make our end-to-end approach, including our synthetic datasets and replication code, publicly available on Github: https://github.com/primeqa/primeqa.

Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers faithfully reflect retrieved documents is difficult: large language models can check long contexts but are too slow and costly for interactive services, while lightweight classifiers operate within strict context limits and frequently miss evidence outside truncated passages. We present the design of a real-time verification component integrated into a production RAG pipeline that enables full-document grounding under latency constraints. The system processes documents up to 32K tokens and employs adaptive inference strategies to balance response time and verification coverage across workloads. We describe the architectural decisions, operational trade-offs, and evaluation methodology used to deploy the verifier, and show that full-context verification substantially improves detection of unsupported responses compared with truncated validation. Our experience highlights when long-context verification is necessary, why chunk-based checking often fails in real documents, and how latency budgets shape model design. These findings provide practical guidance for practitioners building reliable large-scale retrieval-augmented applications. (Model, benchmark, and code: https://huggingface.co/llm-semantic-router)

Recent work has shown that small distilled language models are strong competitors to models that are orders of magnitude larger and slower in a wide range of information retrieval tasks. This has made distilled and dense models, due to latency constraints, the go-to choice for deployment in real-world retrieval applications. In this work, we question this practice by showing that the number of parameters and early query-document interaction play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that rerankers largely outperform dense ones of similar size in several tasks. Our largest reranker reaches the state of the art in 12 of the 18 datasets of the Benchmark-IR (BEIR) and surpasses the previous state of the art by 3 average points. Finally, we confirm that in-domain effectiveness is not a good indicator of zero-shot effectiveness. Code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git

Large reasoning models (LRMs) have demonstrated strong performance in complex, multi-step reasoning tasks. Existing methods enhance LRMs by sequentially integrating external knowledge retrieval; models iteratively generate queries, retrieve external information, and progressively reason over this information. However, purely sequential querying increases inference latency and context length, diminishing coherence and potentially reducing accuracy. To address these limitations, we introduce HDS-QA (Hybrid Deep Search QA), a synthetic dataset automatically generated from Natural Questions, explicitly designed to train LRMs to distinguish parallelizable from sequential queries. HDS-QA comprises hybrid-hop questions that combine parallelizable independent subqueries (executable simultaneously) and sequentially dependent subqueries (requiring step-by-step resolution), along with synthetic reasoning-querying-retrieval paths involving parallel queries. We fine-tune an LRM using HDS-QA, naming the model HybridDeepSearcher, which outperforms state-of-the-art baselines across multiple benchmarks, notably achieving +15.9 and +11.5 F1 on FanOutQA and a subset of BrowseComp, respectively, both requiring comprehensive and exhaustive search. Experimental results highlight two key advantages: HybridDeepSearcher reaches comparable accuracy with fewer search turns, significantly reducing inference latency, and it effectively scales as more turns are permitted. These results demonstrate the efficiency, scalability, and effectiveness of explicitly training LRMs to leverage hybrid parallel and sequential querying.

In real-world Tool-Integrated Reasoning (TIR) scenarios, where LLMs interleave reasoning with external tool calls, a major source of inefficiency is that the toolcalls create pauses between LLM requests and cause KV-Cache eviction, forcing recomputation. Also, the long, unfiltered response returned by external tools inflates the KV-Cache, so each decode step spends more time loading the growing cache and thus becomes steadily slower as context length increases. However, existing efficiency metrics like token counts and toolcall counts fail to capture the real model inference latency. To address this, we introduce PTE (Prefill Token Equivalents), a hardware-aware TIR-efficiency metric that unifies internal reasoning and external tool-use costs while explicitly accounting for non-reusable KV-Cache and long-tool-response scenarios. Validation in a high-concurrency industrial setting indicates that PTE aligns significantly better with wall-clock latency than standard token counts, while maintaining consistent efficiency rankings across diverse hardware profiles. We conduct extensive experiments across five TIR benchmarks, quantify their PTE costs, and identify four inefficiency patterns that appear in TIR. We also discover that trajectories with higher PTE costs tend to have lower reasoning correctness, indicating that simply using more tools does not improve the quality of the answer.

Reasoning-augmented search agents such as Search-R1, trained via reinforcement learning with verifiable rewards (RLVR), demonstrate remarkable capabilities in multi-step information retrieval from external knowledge sources. These agents address the limitations of their parametric memory by dynamically gathering relevant facts to address complex reasoning tasks. However, existing approaches suffer from a fundamental architectural limitation: they process search queries strictly sequentially, even when handling inherently parallelizable and logically independent comparisons. This sequential bottleneck significantly constrains computational efficiency, particularly for queries that require multiple entity comparisons. To address this critical limitation, we propose ParallelSearch, a novel reinforcement learning framework that empowers large language models (LLMs) to recognize parallelizable query structures and execute multiple search operations concurrently. Our approach introduces dedicated reward functions that incentivize the identification of independent query components while preserving answer accuracy through jointly considering correctness, query decomposition quality, and parallel execution benefits. Comprehensive experiments demonstrate that ParallelSearch outperforms state-of-the-art baselines by an average performance gain of 2.9% across seven question-answering benchmarks. Notably, on parallelizable questions, our method achieves a 12.7% performance improvement while requiring only 69.6% of the LLM calls compared to sequential approaches.

The performance of Retrieval Augmented Generation (RAG) systems relies heavily on the retriever quality and the size of the retrieved context. A large enough context ensures that the relevant information is present in the input context for the LLM, but also incorporates irrelevant content that has been shown to confuse the models. On the other hand, a smaller context reduces the irrelevant information, but it often comes at the risk of losing important information necessary to answer the input question. This duality is especially challenging to manage for complex queries that contain little information to retrieve the relevant chunks from the full context. To address this, we present a novel framework, called FB-RAG, which enhances the RAG pipeline by relying on a combination of backward lookup (overlap with the query) and forward lookup (overlap with candidate reasons and answers) to retrieve specific context chunks that are the most relevant for answering the input query. Our evaluations on 9 datasets from two leading benchmarks show that FB-RAG consistently outperforms RAG and Long Context baselines developed recently for these benchmarks. We further show that FB-RAG can improve performance while reducing latency. We perform qualitative analysis of the strengths and shortcomings of our approach, providing specific insights to guide future work.

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.

In this paper, we investigate a problem of actively learning threshold in latent space, where the unknown reward g(gamma, v) depends on the proposed threshold gamma and latent value v and it can be only achieved if the threshold is lower than or equal to the unknown latent value. This problem has broad applications in practical scenarios, e.g., reserve price optimization in online auctions, online task assignments in crowdsourcing, setting recruiting bars in hiring, etc. We first characterize the query complexity of learning a threshold with the expected reward at most epsilon smaller than the optimum and prove that the number of queries needed can be infinitely large even when g(gamma, v) is monotone with respect to both gamma and v. On the positive side, we provide a tight query complexity Theta(1/epsilon^3) when g is monotone and the CDF of value distribution is Lipschitz. Moreover, we show a tight Theta(1/epsilon^3) query complexity can be achieved as long as g satisfies one-sided Lipschitzness, which provides a complete characterization for this problem. Finally, we extend this model to an online learning setting and demonstrate a tight Theta(T^{2/3}) regret bound using continuous-arm bandit techniques and the aforementioned query complexity results.

Retrieval-augmented generation stores all content indiscriminately, degrading accuracy as noise accumulates. Parametric approaches compress knowledge into weights, precluding selective updates. Neither mirrors biological memory, which gates encoding based on salience and archives rather than deletes superseded information. We introduce write-time gating that filters incoming knowledge objects using composite salience scores (source reputation, novelty, reliability) while maintaining version chains that preserve prior states. Using real LLM evaluation without oracle access to quality labels, write gating achieves 100 percent accuracy versus 13 percent for ungated stores. The critical finding emerges under distractor scaling: at 8:1 distractor ratios, read-time filtering (Self-RAG) collapses to 0 percent while write gating maintains 100 percent, revealing a structural advantage of write-time over read-time curation. Validation on Wikipedia (20 entities), procedurally generated pharmacology data, and 2026 arXiv papers confirms these findings. The gating advantage scales inversely with parametric memory support: +25pp for Wikipedia, +48pp for post-cutoff arXiv, +65pp for procedural data with zero training knowledge. Signal ablation confirms the method does not depend on oracle-correlated metadata. Write gating matches Self-RAG accuracy at one-ninth the query-time cost.

Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.

Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Rapidly growing demand strains this paradigm, and cloud providers struggle to scale infrastructure at pace. Two advances enable us to rethink this paradigm: small LMs (<=20B active parameters) now achieve competitive performance to frontier models on many tasks, and local accelerators (e.g., Apple M4 Max) run these models at interactive latencies. This raises the question: can local inference viably redistribute demand from centralized infrastructure? Answering this requires measuring whether local LMs can accurately answer real-world queries and whether they can do so efficiently enough to be practical on power-constrained devices (i.e., laptops). We propose intelligence per watt (IPW), task accuracy divided by unit of power, as a metric for assessing capability and efficiency of local inference across model-accelerator pairs. We conduct a large-scale empirical study across 20+ state-of-the-art local LMs, 8 accelerators, and a representative subset of LLM traffic: 1M real-world single-turn chat and reasoning queries. For each query, we measure accuracy, energy, latency, and power. Our analysis reveals 3 findings. First, local LMs can accurately answer 88.7% of single-turn chat and reasoning queries with accuracy varying by domain. Second, from 2023-2025, IPW improved 5.3x and local query coverage rose from 23.2% to 71.3%. Third, local accelerators achieve at least 1.4x lower IPW than cloud accelerators running identical models, revealing significant headroom for optimization. These findings demonstrate that local inference can meaningfully redistribute demand from centralized infrastructure, with IPW serving as the critical metric for tracking this transition. We release our IPW profiling harness for systematic intelligence-per-watt benchmarking.

Query rewriting (QR) is a critical technique in e-commerce search, addressing the lexical gap between user queries and product descriptions to enhance search performance. Existing QR approaches typically fall into two categories: discriminative models and generative methods leveraging large language models (LLMs). Discriminative models often struggle with natural language understanding and offer limited flexibility in rewriting, while generative LLMs, despite producing high-quality rewrites, face high inference latency and cost in online settings. These limitations force offline deployment, making them vulnerable to issues like information staleness and semantic drift. To overcome these challenges, we propose a novel hybrid pipeline for QR that balances efficiency and effectiveness. Our approach combines offline knowledge distillation to create a lightweight but efficient student model with online reinforcement learning (RL) to refine query rewriting dynamically using real-time feedback. A key innovation is the use of LLMs as simulated human feedback, enabling scalable reward signals and cost-effective evaluation without manual annotations. Experimental results on Amazon ESCI dataset demonstrate significant improvements in query relevance, diversity, and adaptability, as well as positive feedback from the LLM simulation. This work contributes to advancing LLM capabilities for domain-specific applications, offering a robust solution for dynamic and complex e-commerce search environments.

A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder dense retrieval (DR) models recently. A dense text retrieval model uses a single vector representation per query and passage to score a match, which enables low-latency first stage retrieval with a nearest neighbor search. Increasingly common, training approaches require enormous compute power, as they either conduct negative passage sampling out of a continuously updating refreshing index or require very large batch sizes for in-batch negative sampling. Instead of relying on more compute capability, we introduce an efficient topic-aware query and balanced margin sampling technique, called TAS-Balanced. We cluster queries once before training and sample queries out of a cluster per batch. We train our lightweight 6-layer DR model with a novel dual-teacher supervision that combines pairwise and in-batch negative teachers. Our method is trainable on a single consumer-grade GPU in under 48 hours (as opposed to a common configuration of 8x V100s). We show that our TAS-Balanced training method achieves state-of-the-art low-latency (64ms per query) results on two TREC Deep Learning Track query sets. Evaluated on NDCG@10, we outperform BM25 by 44%, a plainly trained DR by 19%, docT5query by 11%, and the previous best DR model by 5%. Additionally, TAS-Balanced produces the first dense retriever that outperforms every other method on recall at any cutoff on TREC-DL and allows more resource intensive re-ranking models to operate on fewer passages to improve results further.

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.

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.

Recent advances in large language models have demonstrated remarkable effectiveness in information retrieval (IR) tasks. While many neural IR systems encode queries and documents into single-vector representations, multi-vector models elevate the retrieval quality by producing multi-vector representations and facilitating similarity searches at the granularity of individual tokens. However, these models significantly amplify memory and storage requirements for retrieval indices by an order of magnitude. This escalation in index size renders the scalability of multi-vector IR models progressively challenging due to their substantial memory demands. We introduce Embedding from Storage Pipelined Network (ESPN) where we offload the entire re-ranking embedding tables to SSDs and reduce the memory requirements by 5-16x. We design a software prefetcher with hit rates exceeding 90%, improving SSD based retrieval up to 6.4x, and demonstrate that we can maintain near memory levels of query latency even for large query batch sizes.

A core limitation of standard softmax attention is that it does not define a notion of absolute query--key relevance: attention weights are obtained by redistributing a fixed unit mass across all keys according to their relative scores. As a result, relevance is defined only relative to competing keys, and irrelevant keys cannot be explicitly rejected. We introduce Multiscreen, a language-model architecture built around a mechanism we call screening, which enables absolute query--key relevance. Instead of redistributing attention across all keys, screening evaluates each key against an explicit threshold, discarding irrelevant keys and aggregating the remaining keys, thereby removing global competition among keys. Across experiments, Multiscreen achieves comparable validation loss with approximately 40% fewer parameters than a Transformer baseline and enables stable optimization at substantially larger learning rates. It maintains strong performance in long-context perplexity and shows little to no degradation in retrieval performance well beyond the training context length. Notably, even at the training context length, a Multiscreen model with approximately 92% fewer parameters consistently outperforms a larger Transformer in retrieval accuracy. Finally, Multiscreen reduces inference latency by up to 3.2times at 100K context length.

Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for the previous queries issued by the user. Achieving context awareness is challenging due to data sparsity. We present a probabilistic suggestion model that is able to account for sequences of previous queries of arbitrary lengths. Our novel hierarchical recurrent encoder-decoder architecture allows the model to be sensitive to the order of queries in the context while avoiding data sparsity. Additionally, our model can suggest for rare, or long-tail, queries. The produced suggestions are synthetic and are sampled one word at a time, using computationally cheap decoding techniques. This is in contrast to current synthetic suggestion models relying upon machine learning pipelines and hand-engineered feature sets. Results show that it outperforms existing context-aware approaches in a next query prediction setting. In addition to query suggestion, our model is general enough to be used in a variety of other applications.

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