Summarization
-
ABRR: Transforming Temporal Sentence Grounding with Wasserstein-Adaptive Refinement and Precision Ranking
2026-11-09 22:23:50Xiang Fang, Wanlong Fang, Junhao Dong, Daizong LiuAbstract
Temporal Sentence Grounding (TSG) aims to localize temporal segments in untrimmed videos that correspond to natural language queries, a critical task for video understanding with applications in video retrieval, summarization, and human-computer interaction. Despite significant progress driven by transformer-based models, existing TSG methods suffer from two key limitations: quantization errors due to temporal downsampling, which misalign segment boundaries, and suboptimal ranking of predictions based on semantic matching rather than localization precision. To address these challenges, we propose the Adaptive Boundary Refinement and Ranking (ABRR) framework, a novel, model-agnostic post-processing approach that enhances the performance of any TSG model without retraining. ABRR integrates three innovative components: (1) Temporal Distribution Smoothing, which mitigates noise in predicted score distributions using Gaussian kernel convolution; (2) Boundary Refinement via Optimal Transport, which leverages the 2-Wasserstein distance and Sinkhorn iterations to align coarse segment boundaries with true temporal moments, grounded in Monge-Kantorovich optimal transport theory; and (3) Quality-Driven Re-Ranking, which reorders predictions using a composite score balancing localization precision and semantic relevance. By correcting quantization errors and prioritizing accurately localized segments, ABRR achieves substantial improvements over state-of-the-art TSG models. Extensive experiments on benchmark datasets, including Charades-STA, ActivityNet Captions, and QVHighlights, demonstrate consistent gains at stringent IoU thresholds (e.g., IoU=0.7), alongside enhanced ranking performance. The framework's computational efficiency and compatibility with existing models make it a versatile and impactful solution for real-world TSG applications.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13310
PDF
-
SpecCompact: Accelerating LLM Agent Context Compaction with Slot-Parallel Semantic Speculative Verification
2026-11-04 18:34:41Yulu An, Yifei Feng, Xiangyang YinAbstract
LLM agents use context compaction to manage growing interaction histories, but summarizing long histories with large models can introduce substantial delays. Compaction therefore requires balancing information retention against latency. We observe that structured summary slots can retain information when generated independently. Based on this observation, we present SpecCompact, a framework that accelerates compaction through slot-parallel semantic speculation. SpecCompact fine-tunes a small drafter and generates slots in parallel. The target model verifies each proposed line and repairs rejected content, while subsequent drafting uses the updated slot prefix. System optimizations further reduce repeated context processing and model calls. Across AppWorld and $\tau^3$ benchmarks with two target models, SpecCompact achieves $2.04$--$5.63\times$ compaction speedups over Hermes-style summarization. Separate downstream evaluations reveal model- and task-dependent performance trade-offs. A user study within Hermes further shows an $8.68\times$ median compaction speedup.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06876
PDF
-
SAUCE: Summary Analysis Using Conversation Entailment
2026-11-04 17:25:40Man-Ling Sung, Hemanth Kandula, Jeff Ma, William Hartmann, Matthew SnoverAbstract
With the growing need for evaluating Large Language Models (LLMs) and their applications to speech, challenges persist in summarizing and evaluating conversations that lack a clear end goal. We introduce SAUCE -- a reference-free, fact-based evaluation pipeline for cross-lingual conversational speech summarization. It measures the accuracy and the fact coverage of a summary through the entailment between conversation and text. We compare SAUCE against several popular summarization metrics and demonstrate the effectiveness of capturing information loss due to transcription and translation error and identifying broken summaries. Crucially, unlike black-box LLM evaluators or dense embedding metrics, SAUCE is inherently explainable: it maps summary scores to discrete, verifiable facts, allowing users to pinpoint exact hallucinations or omissions. We illustrate how this interpretability helps developers systematically profile LLM behaviors and gives end-users an actionable tool to verify summary accuracy in noisy, real-world conditions. Preliminary investigations show SAUCE strongly align with human judgment.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06812
PDF
-
Tools Need Not Speak in Text: Latent Context Compression for Agents
2026-11-04 13:32:36Yuetong Liu, Zhehao Zhou, Yitong Zhang, Haorui Chen, Jia LiAbstract
Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead and dilute the agent's attention to task-relevant information. Existing token pruning and summarization methods remain constrained by discrete text representations, limiting the achievable compression ratios. In this work, we challenge the prevailing assumption that agents must consume tool observations as explicit text tokens. To this end, we propose Coca-Cola, a continuous latent context compression model for LLM agents. Coca-Cola compresses tool observations into latent tokens and embeds them into the input embedding space of the agent. We further introduce Action-Preserving Training, which aligns the agent's next-action distributions under full and compressed observations. This trains the compression model to learn action-sufficient latent tokens that retain decision-critical information. Experiments with web-search agents on four QA benchmarks and two model families show that Coca-Cola reduces the agent's token consumption by 70.01%-89.24% and end-to-end runtime by 24.45%-55.97%, while consistently improving task performance. These results suggest that Coca-Cola offers a promising approach for context compression in agents. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06500
PDF
-
Presentation Sensitivity in Typed Decision Models for Subjective Text Evaluation
Abstract
Typed decision models offer structured choices, scores, and probabilities for low-cost automated evaluation. We present a controlled audit of presentation sensitivity in Jev, Clef Flash, and Perplexity Decider across native choice and score interfaces. Across six datasets with 9,000 multiply annotated humor, helpfulness, and summarization items, we collect 702,000 judgments under interventions that vary positions, identifiers, authorship claims, endorsements, decision framing, and rating rubrics while preserving the evaluated texts. Jev's second-position probability advantage reaches 6.11 percentage points on summaries; reversing reader endorsements changes Perplexity's selected humor text on 40.40% of pairs; and rejection framing reduces Clef's summary agreement with human preferences by 23.36 points. Rating formats also shift score levels while often preserving rankings. Across these findings, repeatability, presentation robustness, and human alignment emerge as distinct properties of an evaluator. Reliable use therefore requires validating the decisions and score interpretations on which an evaluation pipeline depends.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06384
PDF
-
Training-Free Character-Length Control in Summarization with Diffusion Language Models
2026-11-04 11:32:20Steffen Castle, Nils Feldhus, Christopher Ebert, Leonhard Hennig, Sebastian M\"ollerAbstract
Summarization with a fixed character length is important for tasks such as headline and article preview generation, where text must fit an exact space. Autoregressive language models (LMs) struggle with precise character-length control: training-based methods require task-specific fine-tuning, while zero-shot prompting strategies achieve only approximate compliance. We propose DELTA (Diffusion Expected Length Targeting Algorithm), a training-free inference-time method for masked diffusion LMs that estimates expected character length at each denoising step and dynamically inserts or removes masked positions to steer toward a target length. DELTA requires no fine-tuning and is designed for off-the-shelf masked diffusion LMs. Across three summarization benchmarks, it reduces character-length errors by an order of magnitude compared to baselines while maintaining competitive summary quality in both automatic and human evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06371
PDF
-
Clips2Story: Training-Free Video Storyboarding and Editing Using Multimodal Retrieval-Embedded Generation
2026-11-04 05:37:16Junnuo Wang, Weihan Xu, Hao-Wen DongAbstract
Video editors often work with large collections of fragmented footage and must select and organize relevant clips into a coherent story. However, many existing video editing and summarization methods assume a temporally ordered source video and aim to preserve its original narrative and temporal structure. In this paper, we introduce Clips2Story, a training-free, LLM-based pipeline that enables users to create keyword-specified short videos from a pool of video clips. Given a pool of clips and a user-specified keyword, we first extract text-based multimodal descriptors for each clip and retrieve the clips most relevant to the keyword. We then provide the textual descriptors of these candidate clips to an LLM, which selects and arranges them into an editable storyboard with connective narrations. Finally, we assemble the selected clips and retrieve accompanying visuals for the narrations to compose the output video. To evaluate the proposed pipeline, we construct a synthetic evaluation dataset from 100 long-form videos across five genres by segmenting each video into short clips using a scene-change detection model and shuffling the resulting clips to remove their temporal order. Through objective evaluation and qualitative examples, we demonstrate that Clips2Story can effectively retrieve keyword-relevant clips and compose coherent storyboards based on user-specified keywords. Human evaluation further shows that Clips2Story outperforms a strong baseline in terms of narrative coherence, keyword alignment, and overall realism.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05992
PDF
-
SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories
2026-11-03 19:10:50Mingxuan Li, Huanzhi Mao, Ruitao Zheng, Jarod Stanbury James, Yunze Li, Natanya Anderson, Joseph E. Gonzalez, Alex DimakisAbstract
AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons. Yet existing benchmarks fall short of real knowledge work: many rely on synthetic data or isolated tasks, missing the complex, multi-party dynamics of collaborative projects, where critical information is scattered across conversations, code, and evolving decisions. Even simple workplace questions may require locating relevant channels and direct messages, recovering context from long discussions, inspecting repository state, reconciling stale or conflicting evidence, and synthesizing across sources. We introduce SlackBench, a benchmark for evaluating agents on realistic research and engineering workflows that require joint reasoning over workplace communication and evolving repository state. Grounded in privacy-preserving reenactments of real academic research projects, SlackBench provides reproducible environments with realistic multi-party dialogue, evolving decisions, and corresponding code changes grounded in GitHub repositories and Google Docs. It contains 140 queries spanning heterogeneous-source agentic search, abstention on unanswerable or false-premise questions, goal-directed summarization, and circumstance inference over long conversations. These tasks are not reducible to static corpus question answering: agents must determine which conversations matter, traverse threads, inspect repository state, and synthesize evidence across communication and code artifacts. Across 33 frontier models and agent harnesses, the best system scores around 80% and most agents score below 66%, highlighting substantial headroom for improvement. SlackBench thus provides an extensible framework for evaluating agents in collaborative work environments. The SlackBench dataset is available at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2611.05512
PDF
-
Sparse Text Diffusion under Dual Budgets: Context Connectivity and Expert Activation
2026-10-30 09:43:20Alexandros Christoforos, Chadbourne Davis, Paul RajAbstract
Long-context diffusion repeatedly pays for both token interaction and feed-forward computation. We formulate these costs as two separate budgets: the edges available to an attention graph and the experts activated for each token. This view connects local, dilated, and global attention with conditional expert computation without assuming that sparsity alone preserves document-level information. We specify normalized masked attention, distinguish denoising depth from sampling iterations, and derive graph and compute bounds. A reported sparse-expert configuration, denoted DualBudget, is analyzed across scientific summarization, multi-hop question answering, dialogue, and sentence-pair prediction. All supplied table measurements are retained. The length study shows gains over the listed baselines through 16K, together with measurable degradation as length increases. Ablations reveal mixed changes across the three reported scores, while the cost record indicates a 20% reduction relative to DiffuSeq under an unspecified timing convention. The analysis separates these observations from unmeasured claims about training speed, absorbing states, global coherence, and deployment memory.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41487
PDF
-
Comparative Evaluation of LLM-Based Review Paradigms for Academic Paper Quality Assessment
2026-10-30 08:02:25Fan Huang, Hongyu ZhouAbstract
Growing submission volumes have renewed interest in using large language models (LLMs) to support peer review. It remains unclear how such evaluation should be structured, how much the model matters, and whether LLM scores predict research impact. We evaluate five paradigms across three input representations and three LLMs on 232 stratified ICLR 2025 submissions. Direct absolute rating matches comparative ranking on rank correlation with human scores, yet compresses most predictions above the accept threshold, flagging almost none of the papers reviewers scored below it. A base-rate-matched recalibration control locates the cause: comparative ranking supplies placement, not better ordering, and after recalibration Direct Rating reaches higher agreement than Elo while making 24% as many API calls. Abstract-only input beats full-paper summarization, and model choice matters as much as paradigm choice. Replicating on all 11,513 scored submissions reproduces these patterns, shows absolute agreement depends on the evaluated set's score spread, and finds none beating an always-reject baseline in accuracy. Human scores track citations better than any paradigm, with one exception: Group Rating retains its citation correlation after controlling for human scores, and alone ranks within the accepted pool. Ranking quality alone cannot assess review quality; calibration, thresholds, model, and target outcome all matter.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41391
PDF
-
S2TDR: Structured Multimodal Reconstruction for Sticker-Aware Dialogue Understanding
2026-10-30 02:57:24Yuanchen Shi, Fang KongAbstract
Stickers are widely used in social media dialogues to express affect, stance, and intent beyond literal text. Their meanings are often non-literal and context-dependent, making them difficult to handle with generic visual fusion or standalone captioning. We propose Sticker-to-Text Dialogue Reconstruction (S2TDR), a structured multimodal reconstruction framework that converts sticker turns into contextually appropriate textual utterances. S2TDR decomposes sticker interpretation into visual cue extraction, affective-intent inference, and context-aware dialogue reconstruction, using OCR text only as an auxiliary cue when available. The reconstructed dialogue can then be consumed by existing text-based dialogue models. Experiments on sentiment analysis, intent recognition, and dialogue summarization show that S2TDR generally improves multiple downstream models over direct sticker integration methods. Further analyses on component ablations, OCR-empty stickers, and reconstruction quality indicate that structured reconstruction provides an interpretable and effective way to integrate sticker semantics into dialogue understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41176
PDF
-
Cross Lingual Abstractive Summarization for Marathi
2026-10-28 04:34:32Asang Dani, Shailesh R SatheAbstract
Text summarization is an important task for advancing natural language processing (NLP) research and applications in Indic languages. Despite progress in extractive and abstractive summarization, both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these languages. Recent advances in Transformer architectures, pretrained language models (PLMs), and dataset availability offer new opportunities to address this gap. In this work, we construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2, an Indic neural machine translation model. We evaluate the resulting models using ROUGE, chrF and chrF++ metrics, focusing primarily on Marathi-to-English summarization due to computational constraints. We also discuss the applicability of our approach to the English-to-Marathi direction. Our experiments demonstrate that leveraging a pretrained translation model yields substantially better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work on cross-lingual summarization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38267
PDF
-
CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models
2026-10-27 06:52:54Jingpu Yang, Tianhao Li, Fengxian Ji, Yufeng Wang, Shuxin Zheng, Xiaoqing ZhangAbstract
Continual learning requires large language models to acquire new knowledge and capabilities while retaining what they have learned. Fine-tuning and replay support acquisition and retention, but deciding whether incoming examples need supervision and which historical examples to revisit remains a challenge. We propose Compatibility-Aware Memory Replay (CAMR), an adaptive framework that jointly controls current-example supervision and historical replay. CAMR combines compatibility checks with a learned memory gate to guide an online policy over three actions: learning incoming examples with general replay, jointly reinforcing compatible related examples, and skipping direct supervision of verified mastered duplicates. The policy learns from acquisition, retention, and training-cost feedback under a bounded per-arrival replay budget. We evaluate CAMR with Qwen3-8B-Base on continual factual updating and cross-task and cross-domain learning. On WikiBigEdit, CAMR consistently leads evaluated methods in Original Match from 3K to 100K facts, reaching 93.66% after just 3K facts and surpassing Full-history Replay (LoRA) after 100K facts. It also achieves the highest final scores on all four selected TRACE tasks and maintains or improves earlier-task performance relative to post-acquisition levels in a sequence spanning financial question answering, mathematical reasoning, code generation, and summarization.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36734
PDF
-
MemVLN: Streaming Episodic Memory for Vision-Language Navigation
2026-10-26 09:13:13Yan Wang, Jiangyong Huang, Baoxiong Jia, Siyuan HuangAbstract
Vision-language navigation (VLN) requires an embodied agent to follow language instructions through 3D environments. Maintaining persistent episodic memory remains a challenge for VLM-based streaming agents in long-horizon navigation. We present MEMVLN, a streaming episodic memory framework that maintains a bounded bank of compressed perceptual features annotated with timesteps and action-derived relative poses, and produces compact memory tokens via cross-attention. We pair the proposed memory with a frozen pretrained geometry encoder. To learn the memory module, we design a masking-based trajectory summarization task with multi-granularity sub-trajectory decomposition, encouraging route reconstruction exclusively from episodic memory. Under navigation training restricted to the official R2R/RxR trajectories, MEMVLN achieves state-of-the-art performance on most reported metrics on standard VLN-CE benchmarks. Long-horizon analyses further characterize when episodic memory is useful. For physical evaluation, we collect 30 instruction-conditioned episodes in one physical scene, use 24 as demonstrations for post-training, and hold out six for testing. On the held-out episodes, MEMVLN improves success over the VLM baseline from 17% to 40%, and post-training further raises it to 47%.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35066
PDF
-
ComBeautify: Leveraging Code Change Summaries for Conventional Commit Generation
2026-10-25 15:31:39Rishi Raj, Aashray Tandon, Nikolay Matyunin, Jibesh PatraAbstract
Modern software development relies on version control systems such as Git to track changes and facilitate collaboration. While commit messages are crucial for conveying developer intent, they do not affect program functionality; as a result, developers often lack motivation to write meaningful ones. The Conventional Commits Specification (CCS) addresses this with a structured format and guidelines that help developers express the intent of a change, improving clarity and enabling automation. Yet, developers frequently struggle to express intent while adhering to the format. In particular, they may misclassify commits due to the large number of possible categories or the lack of project-specific guidance. We introduce ComBeautify, an approach that automatically generates CCS-compliant commit messages. Our hybrid approach leverages context-preserving summarization of Git diffs with large language models (LLMs) to improve commit classification accuracy under CCS. Rather than relying on manually curated category definitions, we learn them from historical commits. We also propose a method for automatically generating the CCS description component. Our empirical evaluation across 13 languages, 6,500 open-source repositories, and over 20 million commits provides long-term insights into CCS adoption, revealing increasing compliance. Our evaluation on twenty popular repositories reveals the limitations of approaches guided by generic category definitions, and shows that ComBeautify, when trained on project-specific data, outperforms baselines by up to 3x. Additionally, using a dataset of 2,000 manually curated commits, we validate our summarization approach, achieving up to 95.25% accuracy and surpassing baselines. These findings emphasize the need for adaptable, context-aware AI methods for commit classification and CCS-compliant commit message generation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34374
PDF
-
Benchmarks Are Surprisingly Compaction-Friendly
2026-10-22 18:15:54Jeanne Salle, Hardik Bhatnagar, Matthias Bethge, Sahar Abdelnabi, Maksym AndriushchenkoAbstract
Long horizon agentic tasks are now pushing LLM agents past their context window. To continue the task, the agent scaffold has to free up the context window, a process known as context compaction. Compaction is generally lossy by design: agents can silently lose task constraints, instructions, or their reasoning behind earlier decisions. Although compaction is a standard component of coding agent scaffolds, it has not been studied systematically with frontier models on realistic, long horizon agentic tasks. Previous work evaluate smaller open weight models on toy or synthetic trajectories. We fix the agent scaffold (OpenCode), implement five compaction strategies inside it, and evaluate three frontier models on three long horizon benchmarks (PaperBench, ProgramBench, PostTrainBench). For the two 1M context models, the compaction threshold does not measurably affect the task performance, whereas GPT-5.3-Codex, the model with the smallest context window, performs worse at lower thresholds on PaperBench and, less clearly, on PostTrainBench. No compaction method outperforms default self-summarization, and methods that discard more content cost some models up to 20 points while leaving other models the same. Compaction can, however, silently remove task constraints: on ProgramBench, the first compaction summary already drops about one third of the task's anticheating rules on average, and this rises monotonically with the number of compactions. On real user-agent sessions from SWE-chat, instructions about how the agent should work and what it should not do are dropped around 6 times more than specifications of what to build. We argue that current benchmarks are compaction-friendly: i.e., the objective is fixed and the agent's progress stays on disk, so most of what compaction discards can be recovered, except constraints that don't exist anywhere else.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31778
PDF
-
From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries
2026-10-22 15:58:57Bayram Ayadi, Florian Geissler, Johanna SchmidhuberAbstract
As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large Language Models (LLMs) offer a promising mechanism for translating structured clinical information into readable narratives, but this process may introduce semantic drift, where clinically precise meaning is distorted during simplification. We investigate evidence-grounded health summarization for menstrual health monitoring using a constrained generation framework that combines structured evidence conditioning with Retrieval-Augmented Generation (RAG) using a prompt-based constrained generation framework. We evaluate semantic alignment using Natural Language Inference (NLI), atomic factuality metrics, and readability measures. Across three LLMs and 4,500 generated summaries, explicit grounding constraints consistently improve clinical alignment, particularly by improving uncertainty preservation and, once faithfulness is evaluated against retrieved evidence, generally preserving or improving faithfulness, while effects on omission remain model-dependent. We also find that improved clinical alignment comes at the cost of increased reading difficulty and medical terminology. These findings highlight the need to jointly evaluate faithfulness, uncertainty preservation, and readability when developing patient-facing medical LLM systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31467
PDF
-
Multi-level Encoder with Global Topic for Task-oriented Dialogue Summarization
2026-10-21 02:41:38Zhuoqi He, Peijie Huang, Yuhong Xu, Youming Peng, Mingzhi Xu, Xinyang LinAbstract
Task-oriented dialogue summarization aims to automatically extract key information to generate domain summaries to improve service efficiency and quality. Task-oriented dialogue is inherently logical and surrounds specific topic. How to effectively capture the dialogue topic and the most salient information becomes one of the major challenges of this task. In this paper, we propose a task-oriented dialogue summarization model utilizing a multi-level encoder with global topic (MLEGT). This model discovers temporal and spatial dependencies through a multi-level encoder, while simultaneously obtaining a simple yet effective global topic in the process of graph construction. It not only captures the crucial details but also breaks the long-range limit and discover the intrinsic structure across the dialogue. Then, a global topic guided pointer mechanism is added into the summrizer to capture ignored but important information, which is helpful to improve the accuracy of the summary. A comprehensive study of two public datasets, including a real-world large-scale Chinese police interrogation dataset and a medical reporting service dataset proves the superiority of our method on several strong baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29097
PDF
-
Cache Engineering for Agents
2026-10-20 17:32:24Tianyu Fu, Ruoxi Wang, Zihan Min, Zhongqi Ren, Zhihao Li, Tengxuan Liu, Shengxu Mu, Hanling Zhang, Yu WangAbstract
Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV) cache I/O and storage become the dominant cost. Trajectories can also exceed the LLM's maximum context length, requiring control over active cache growth. Prior work uses context engineering to reduce cache size by trimming or summarizing history. However, modifying the trajectory prefix invalidates subsequent cached states and triggers costly re-prefilling of retained context. Task accuracy can also suffer when too little context is retained to limit re-prefill costs. We propose cache engineering as a new scheme. It allows agents to directly control their active KV cache without modifying the trajectory or re-prefilling retained context. Specifically, agents can proactively use drop to exclude selected cache from future attention and repos to adjust retained keys' position encodings. We formalize these cache operations and identify history dependence as a serving challenge: identical token sequences can yield different cache states under different cache operation sequences, making prefix matching insufficient for correct cache reuse. Thus, we co-design the AKV serving engine. It provides a stateless interface compatible with existing serving APIs, while internally managing stateful cache reuse, eviction, and restoration. Experiments show that a tool-response rolling-drop cache policy improves average benchmark scores by 1.7 points and reduces average cost by 27.7%, compared with conventional threshold-triggered summarization. With AKV, it achieves up to 1.2x the output throughput and a 1.5x speedup in P95 request latency. Recursive self-improvement of cache policies further reduces cost by 7.1% over expert design. Our code is at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28577
PDF
-
M-Plan: Comprehensive Planning For LLM Agents with Memory Arrangement
2026-10-19 16:30:42Ziyang Liu, Jiakang Yuan, Jiayuan Fan, Tao ChenAbstract
Large language model (LLM)-based agents have recently demonstrated outstanding performance in single-turn tasks, yet they continue to struggle with long-horizon tasks, particularly in environments without prior training. A key limitation of single LLMs is their difficulty in processing long contexts, which stems from weaknesses in continuous decision-making and reasoning capabilities. Although existing multi-agent systems (MAS) equipped with long-term memory bases can partially address this gap, they mostly rely on knowledge reuse or summarization, an approach that is often constrained by directly retrieval without any adaptation for the current task, while the retrieved memory may contain much history noises waiting to be preprocessed. In contrast, MAS characterized by task-specific guidance often lack long-term memory specifically designed for the guidance. To address these challenges, we propose M-Plan, a closed-loop MAS framework that integrates long-term and short-term memory. By combining global-local and past-current guidance, M-Plan enhances agents' performance on multi-turn tasks while maintaining a plug-and-play design. During task execution, agents receive task-specific milestones and insights, and are provided with local hints only when confusion arises, which form global-local guidance together. These guidance generation and utilization construct the short-term memory as well. After task completion, relevant information about the current task is optimized or reorganized before being sent to the long-term memory storage for future retrieval. The designments mentioned above build a comprehensive framework different from other individual long-term or short-term memory works. Extensive experiments on multi-turn tasks including ALFWorld, Webshop, and PDDL across diverse models demonstrate that M-Plan outperforms multiple baseline methods in both accuracy and efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27032
PDF
