跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 10:35 — 2026-11-16 10:35(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-14 15:09库内论文最新更新时间:2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 42 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.17167

行动者、评判者还是教师?理解长程智能体中的决策模型

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

Haochen Liu, Qianhao Zhu, Zixuan Wang, Dingming Li, Tongbo Chen, Peng Qiu, Yingqi Qu, Weiming Lu 等 10 位作者

AI 速读 基于摘要

论文比较决策模型作为行动者、评判者与教师三种角色,提出表现差的行动者仍可能通过事后评判成为好教师。

cs.AI · cs.CL

查看原文摘要

Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning. Prior work has studied them mainly as actors, judging their usefulness by how well they act. We ask whether a decision model that acts poorly can still teach well. We compare three decision models and three general LLMs as actors and judges on ALFWorld, and use JEV as a teacher on ALFWorld and WebShop. As actors, all six models are pulled away from a subgoal that must come first by an easier one. As judges that see the whole trajectory, the same models credit the steps toward that subgoal, and asking whether each action helped, rather than whether the task will succeed, separates useful from useless actions. As a teacher, JEV raises a Qwen2.5-1.5B policy over GRPO from 72.8% to 82.9% success on ALFWorld and from 56.8% to 71.4% on WebShop. These results suggest that a poor actor can still teach well, because judging an action after the episode ends reveals the consequences that acting must anticipate. Code is available at https://github.com/ZJU-REAL/decision-agents.

新论文 · v1arXiv:2611.15777

SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models

Lichen Li, Ziping Dong, Sicheng Feng, Qi Li, Xinchao Wang

原文摘要

System One models promise fast, general-purpose decision-making without lengthy token generation. However, understanding their capability spectrum and decision reliability requires more than aggregate performance on current benchmarks. Existing evaluations often provide limited insight into the breadth of model capabilities and the reliability of their decisions. We introduce SO-Arena, a benchmark characterizing the capability spectrum and decision reliability of System One models across 11 domains and five capability families. For the capability spectrum, SO-Arena offers evidence-grounded evaluation through reliable sources and manual verification of reference labels against model-visible inputs; fine-grained capability assessment through domain-specific difficulty criteria; and realistic interactive evaluation, where models iteratively execute actions in sandboxes. Reasoning-intensive tasks further enable system one-two comparison. Beyond accuracy, SO-Arena assesses decision reliability through two complementary measures: decision stability under controlled option-set changes and missing-answer recognition when no valid option is available. Evaluations across 21 models reveal that the benefits of scaling and additional reasoning vary substantially across domains. More importantly, strong overall performance does not necessarily imply reliable decision-making: the best-performing System One model ranks only seventh in reliability. Together, these findings highlight the need to characterize capability spectrum and decision reliability as complementary dimensions, providing a systematic view of the strengths and limitations of System One models.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.14980

CoLFA: Collaboration-Guided Lightweight Failure Attribution for LLM-Based Multi-Agent Systems

Yufei Luo, Yuchen Ling, Chunrong Fang

原文摘要

Failure attribution in multi-agent systems requires tracing error formation to identify the decisive error step and the responsible agent. However, agents' division of work and information exchange lead to Interleaved Steps and Cluttered Content, requiring models to link executions and check details in lengthy records. This makes it difficult to balance localization accuracy and token cost. We find that multi-agent collaboration also leaves records of how executions connect and content passes between them as results are formed, providing evidence for tracing error formation. Based on this observation, we propose CoLFA (Collaboration-Guided Lightweight Failure Attribution), which uses collaboration cues to organize the attribution input according to how results are formed, determining which steps are examined and how their content is presented. Through Handoff-Guided Step Expansion and Cross-Referenced Content Organization, CoLFA helps the model focus on examining error formation and the role of each decision while reducing the processing of irrelevant and repeated records. Across five settings spanning Who&When and LongRCA and three backbone models, CoLFA achieves the highest exact step-localization accuracy with the lowest token consumption. Compared with individual baselines in each setting, CoLFA improves accuracy by up to 37.50% and reduces token consumption by up to 97.6%.

cs.CL

版本更新 · v3arXiv:2605.22715

AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

Baiyu Chen, Zechen Li, Wilson Wongso, Lihuan Li, Xiachong Lin, Hao Xue, Benjamin Tag, Flora Salim

原文摘要

As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inertial signals are highly dependent on the sensing setup, including body location, mounting position, sensor orientation, device hardware, and sampling protocol. This setup dependence makes it difficult to learn motion representations that transfer across devices and datasets, and limits the broader use of wearable IMUs beyond closed-set recognition. We introduce AnyMo, a geometry-aware framework for setup-agnostic human motion modeling. AnyMo uses physics-grounded IMU simulation over dense body-surface placements to generate diverse and plausible synthetic signals, pre-trains a graph encoder from paired synthetic placement views and masked partial observations, tokenizes multi-position IMU into full-body motion tokens, and aligns these tokens with an LLM for motion-language understanding. We evaluate AnyMo on three complementary tasks: zero-shot activity recognition across 14 unseen downstream datasets, cross-modal retrieval, and wearable IMU motion captioning, where it improves average Accuracy/F1/R@2 by 11.7\%/11.6\%/22.6\% on HAR, increases zero-shot IMU-to-text and text-to-IMU retrieval MRR by 15.9\% and 28.6\%, respectively, and improves zero-shot captioning BERT-F1 by 7.5\%. These results support AnyMo as a generalist model for wearable motion understanding in the wild. Project page: https://anymo-project.github.io.

cs.CV · cs.AI · cs.CL · cs.HC

版本更新 · v6arXiv:2610.16717

Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference

Yuchen Li, Xintong Li, Zongqi Fan, Ken-tye Yong, Nguyen H. Tran

原文摘要

Whether a large language model has a self is usually argued without a way to measure it. We measure a functional self with two levels familiar from biology: a self-index, which marks material as the model's own, as animals tag self-generated signals with a corollary discharge, and self-reference, the ability to recognize what is one's own, as in mirror self-recognition. Our main finding is that language models mark their own messages internally and that recognizing them depends on this mark: no model we tested recognizes its own messages without it, and in the four models we edited, changing the mark removes or creates the recognition. With the same text placed in an Assistant, a User, or a System message of its chat template, Qwen3.8-27B separates its own message from both external ones at all 64 layers and in every held-out text. Asked who wrote a message, it answers "you" with probability 0.77 for its own messages and at most 0.07 for the others. Setting eight coordinates per layer, along which its own message differs most from the same text as a User message, to their User values lowers the rate of "you" to at most 0.05, and the reverse edit makes the model claim a User message, closing at least 41% of the gap. Random directions do neither, and answers about the content stay unchanged. This holds in Qwen3.8-27B without and with thinking, gpt-oss-20b, gpt-oss-120b, and MiMo-V2.6-Distill-Qwen-9B. Across twenty-five open-weight models from fourteen developers, the two levels are nested: no model recognizes its own messages without a self-index (permutation p = 0.004). Without any question, next-token prediction on the model's own message differs from that on the same text in another role, more so as more layers carry the self-index (Spearman rho = 0.82), and the same coordinates carry this difference. These results support the account that self-reference is a readout of a self-index.

cs.CL

新论文 · v1arXiv:2611.13426

BioMem: Agentic Memory for Biomedical LLM Agents

Mingchen Li, Yongkang Xiao, Rumeng Li, Rui Zhang, Hong Yu

原文摘要

Large language models (LLMs) have demonstrated considerable potential in biomedical applications, while agentic memory systems have emerged as a promising approach to preserving and utilizing information across tasks and interactions. However, a fundamental question remains: how effectively and reliably do these systems retain, retrieve, update, and utilize biomedical information? In this study, we systematically investigate agentic memory in the biomedical domain, focusing on task effectiveness, retrieval quality, information fidelity, and long-term robustness. We evaluate five memory approaches across four LLMs in three representative settings: biomedical knowledge reasoning, clinical prediction, and long-term conversational memory. Our analyses reveal how memory construction, evidence relevance, and conversational history shape downstream biomedical performance, highlighting the distinct challenges of retrieving relevant information, preserving its fidelity, and effectively utilizing it for reasoning. Building on these findings, we introduce Hybrid Memory Retrieval and Utilization (HMRU), a training-free framework that jointly enhances evidence accessibility and task-aware utilization to improve biomedical reasoning and long-term conversational memory. HMRU achieves an average relative improvement of 8.6% across biomedical question-answering and conversational memory benchmarks, with additional gains in selected clinical prediction tasks. It further reduces conversational answer errors by 24.9% and closes 48.0% of the performance gap to full-context inference. Our findings provide a systematic characterization of biomedical agentic memory and practical insights into developing more effective and reliable memory-augmented LLM systems.

cs.CL

新论文 · v1arXiv:2611.11299

EASE-KV: Diagnosing the Gap Between Memory Availability and Effective Use

Di Lu, Zechen Li, Xuanyu Yue, Jiabo Fan, Hao Xue, Flora D. Salim

原文摘要

Reusable key-value (KV) memory avoids repeatedly prefilling retrieved text, but stored and injected memories do not necessarily become usable evidence. We present EASE-KV, a controlled framework for understanding this gap under fixed candidates and a frozen language model. EASE-KV separates three interfaces: whether required relations are preserved during encoding, whether preserved memories receive appropriate influence during allocation, and whether outcome supervision can identify useful allocations. Matched experiments show that causal encoding improves compositional accuracy by 25.0 percentage points over block-diagonal encoding, while the tested inference-time bridging methods fail to recover the lost contextual information. With unchanged stored states, diagnostic evidence-guided allocation improves LongMemEval accuracy from 31.2% to 38.4%, demonstrating that memory influence can be controlled without re-encoding. However, controllability does not guarantee learnability: binary correctness provides informative reward contrast for 53.0% of sampled query groups, compared with 73.6% under the evaluated shaped-reward setting. These findings show that effective KV memory requires more than retrieval and injection: the required relations must be encoded, preserved memories must receive appropriate influence, and supervision must distinguish better allocations from worse ones.

cs.CL · cs.AI

新论文 · v1arXiv:2611.09768

语言作为特质、礼貌作为策略:LLM社交推理智能体中语言效应的受控测试

Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents

Yuchen Li, Lisa Liu, Runqi Zou, Shuxuan Kuang, Qingquan Zhang, Julian Togelius

AI 速读 基于摘要

作者在LURK Werewolf框架中只改写同一话语的自然语言表达(语言复杂度范围与礼貌策略),通过重放对局检验这些语言差异是否改变其他LLM智能体的信任判断与行动。

cs.CL · cs.AI

查看原文摘要

Large language model (LLM) agents coordinate through conversation, and the same message can be phrased in simpler or more complex language, bluntly or politely. We test whether such differences change how other agents judge and act, using the LURK Werewolf framework, which separates each utterance's speech-act predicate from its natural-language realization. We rewrite only the realization, check that the game content is preserved, and replay each game day from saved checkpoints against a re-sampled control. We vary linguistic range consistently across a speaker's messages and politeness strategy per utterance. Across 30 games and 4,335 replays, neither manipulation changes the trust other agents place in the speaker, and no effect on votes or night actions survives correction for multiple comparisons; the largest uncorrected effect is that shifting range away from a neutral paraphrase changes about 4 percentage points more of the other players' votes. In natural play, 88% of face-threatening speech is bald on-record regardless of role.

新论文 · v1arXiv:2611.07372

EnvOpt: Automated Optimization for Agent Environments

Mingxuan Li, Huanzhi Mao, Qiuyang Mang, Hanchen Li, Joseph E. Gonzalez, Alex Dimakis

原文摘要

An LLM agent's cost and success depend on its model, its harness, and its environment. In addition to the widely studied directions of parameter tuning and harness optimization, we propose the third direction: optimization over stationary environments. Agents are often deployed in rich environments shared by many tasks, such as a company's Slack workspace or a complex collection of data sources, documents or tickets. We call these environments stationary environments. We introduce EnvOpt, a method for automated end-to-end optimization of stationary environments for any given model and harness, using real or synthetic tasks without needing any graders or reference answers. On AutomationBench, EnvOpt reduces the cost of Claude Haiku 4.5 by 72.7% and raises its pass rate by 14.34%. The same environment transfers to Opus 5, cutting its cost by 68.1% with a 1.34% gain. Added on top of Meta-Harness's optimized harness for Haiku 4.5, it lowers cost by a further 83.4% and adds 11.17% accuracy over Meta-Harness alone. Across 5 benchmarks, EnvOpt significantly reduces the cost of agents while improving or maintaining pass rate, and is transferable to different models and different harnesses. We also discuss common successful and rejected environment optimization strategies during automated optimization. More broadly, our results show that how information is represented to an agent shapes both its cost and its success, making the environment worth optimizing in addition to the parameters and the harness.

cs.AI · cs.CL

版本更新 · v2arXiv:2609.22231

EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems

Zeyu Liu, Jian Zhong, Rongduo Han, Ziyang Wu, Shunye Tang, Chenghao He, Yaxuan Yang, Yihang Qiu 等 15 位作者

原文摘要

Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories. Existing evaluations report end-to-end QA accuracy and cannot determine whether errors arise from encoding, retrieval, or generation. We introduce EvalMem, an operation-level diagnostic framework with three parallel Examiners. For each query, the Encoding Examiner checks whether the target fact is stored, the Retrieval Examiner assesses whether the native retriever returns usable evidence, and the Generation Examiner tests whether the model can answer from oracle evidence. Their outputs form fine-grained multi-label defect codes. To improve store-level diagnosis, we adapt agentic RAG with a recall-first strategy that searches using both the query and source evidence, increasing recall of present evidence on LoCoMo from 70.2% to 95.6%. Evaluations of seven memory systems on LoCoMo, LongMemEval-S, and dynamic DynaMem-Bench identify retrieval as the most frequently attributed failure layer; in default LoCoMo, retrieval defects reach 22.1%, compared with 7.7% for encoding and 6.5% for generation. Guided by this diagnosis, MemWiki, a search-friendly auxiliary structure built from each system's memory export, improves mean accuracy by 2.5 and 2.3 percentage points on LoCoMo and LongMemEval-S, respectively.

cs.CL

新论文 · v1arXiv:2611.02480

Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory

Di Lu, Zechen Li, Hao Xue

原文摘要

Long-term conversational memory faces a timing mismatch: write-time summaries and graphs organize history before a future query is known, while independent retrieval can allocate a limited evidence budget to redundant or fragmented turns. We introduce Chain on Demand (CoD), a query-time evidence organization framework over an unchanged turn-level memory. Given a broad candidate pool, CoD constructs a temporary evidence chain by allocating a fixed anchor budget according to query relevance, lexical diversity relative to selected anchors, and newly covered query terms, followed by deterministic restoration of each selected anchor's same-session neighborhood. The resulting chain is used only for the current query, while the underlying conversational memory remains unchanged. In a paired comparison over all 1,986 LoCoMo questions, CoD achieves 82.2% accuracy on 1,540 non-adversarial questions and 76.3% on all 1,986 questions. On LongMemEval-S, one fixed configuration that indexes both user and assistant turns obtains 86.6% across all 500 questions. These results show that long-term memory can preserve the original conversation while deferring evidence organization until the information need is known.

cs.CL · cs.AI

版本更新 · v6arXiv:2606.02780

Do Value Vectors in Deep Layers Need Context from the Residual Stream?

Muyu He, Yuchen Liu, Qingya Huang, Li Zhang

原文摘要

The success of the transformer architecture is in large part due to its use of attention layers. An attention layer follows the standard neural network paradigm: it takes the residual stream as input and thereby produces context-dependent query, key, and value vectors. However, we find that model performance meaningfully improves when deeper layers learn only a context-free value vector to preserve the original token information, without drawing on any context from the residual stream. When the model has access to this context-free value vector, adding back the context-dependent component provides little additional benefit for aggregate benchmark performance. Such context-free value vectors can be stored as sparse model parameters, eliminating the need to recompute or persistently cache these values. Through systematic ablations on the key design choices for such context-free value vectors, we propose Bank of Values (BoV), a new way of computing value vectors in attention by learning a lookup table of token-specific value vectors for each of the last third of layers. Across 135M and 780M models, BoV improves validation loss over standard attention and, at 780M, the average score across 21 benchmarks, matching the previous best method that adds token information to the value vector with less compute and memory.

cs.CL

版本更新 · v2arXiv:2609.35663

Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context

Muyu He, Yuchen Liu, Ran Tao, Li Zhang

原文摘要

Large language models (LLMs) reliably perform entity copying, in which a model copies tokens referring to an entity, termed entity tokens, from the prompt into its output to answer a question. Although entity copying is straightforward for most LLMs, existing research does not provide a systematic account of which layers specialize in this fundamental task or how other tokens in the same sequence, termed context tokens, influence the model's ability to copy the entity tokens. To address these questions, we conduct experiments on Qwen3-8B using two novel methods: genie-in-a-bottle, which controls exactly which layers can participate in an entity-copying task, and attention lobotomy, which cuts off specific tokens' attention to entity tokens without affecting the remaining attention distribution. We find that two distinct groups of layers in the second half of the model are both necessary and sufficient for entity copying. Moreover, in addition to the decoding position's attention to entity tokens, context tokens' attention to entity tokens also proves necessary for copying the exact tokens, even though context tokens do not store entity information themselves unless they satisfy particular semantic properties. Our findings establish the critical role of late layers in entity copying under the guidance of context tokens, calling for future work on how models propagate and consume entity information.

cs.CL

新论文 · v1arXiv:2610.36013

OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

Xiaomi Embodied Intelligence Team, Yuechen Luo, Chong He, Fang Li, Shaoqing Xu, Jingkai Wang, Menglun Su, Jiaxin Liu 等 32 位作者

原文摘要

General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers' interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.

cs.CL · cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-demo.6ACL Anthology · ACL 2026

AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling

Zhen Lin Hefei University of Technology, Qiujie Xie Westlake University, Minjun Zhu, Shichen Li, QiYao Sun, Enhao Gu, Yiran Ding Westlake University, Ke Sun 等 13 位作者

原文摘要

High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding, reference-guided styling, and native SVG editing, it enables efficient creation and refinement of high-quality scientific illustrations. To facilitate further progress in this field, we release the video at https://youtu.be/10IH8SyJjAQ, the full codebase at https://github.com/ResearAI/AutoFigure-Edit and provide a live demo for easy access and interactive use at https://autofigure.cc/.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-demo.7ACL Anthology · ACL 2026

QFinZero: A Unified Financial Toolchain for LLM-Based Trading Agents

Haochen Luo, Yifan LI, Ho Tin Ko City University of Hong Kong, An Binh Minh, Junjie Xu, Tang Pok Hin City University of Hong Kong, Wang Chak Wong, Gao Yuan 等 11 位作者

原文摘要

Large language model (LLM) agents are increasingly applied to financial decision-making tasks that require interaction with external tools, including market data retrieval, news analysis, and trade execution. However, existing trading systems rely on fragmented and task-specific APIs, resulting in inconsistent schemas, complex integration, and limited reproducibility. We present QFinZero, a unified trading environment for LLM-based financial agents. QFinZero standardizes three core capabilities: (i) multi-frequency market and derivatives data access, (ii) structured news and event retrieval, and (iii) stateful brokerage simulation with explicit order lifecycle management. All tools adopt consistent JSON schemas and time-aligned interfaces, enabling agents to acquire information and execute trades within a coherent framework. By abstracting financial interaction into composable, agent-invokable primitives, QFinZero reduces engineering overhead and supports reproducible evaluation through comprehensive logging and deterministic replay. We argue that such a standardized trading environment is essential for scalable research on LLM-based financial agents.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.119ACL Anthology · ACL 2026

OmniOData: Unleashing Small Language Models for OData Query Generation with Synthetic Data and Reinforcement Learning

Tao Bai, Zhaochen Li, Hongxin Shao, Daniel Dahlmeier

原文摘要

Despite the success of Large Language Models (LLMs) in structured query generation, OData—a critical RESTful protocol for enterprise APIs—remains under-researched due to a lack of high-fidelity, execution-validated datasets. To bridge this gap, we introduce OmniOData, a framework that generates SynOData, the first large-scale OData corpus featuring execution-grounded queries and reasoning traces. Using this corpus, we develop OmniOData-R1 (1.5B–3B parameters), a family of models that match or surpass frontier proprietary systems, such as GPT-4o and Gemini 3, on realistic industrial benchmarks. Our results demonstrate that the synergy of execution-verified synthetic data and Reinforcement Learning (RL) effectively unlocks the latent reasoning of Small Language Models (SLMs), providing a high-performance, low-latency solution for specialized enterprise query generation.The code and data will be released under an open-source license.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.120ACL Anthology · ACL 2026

LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models

Tianchun Li, Haochen Liu, Vishwa Pardeshi, Xingchen Wang, Tianci Liu, Huijun Zhao, Wei Fan, Jing Gao

原文摘要

Small language models (SLMs) are promising for real-world deployment due to their efficiency and low operational cost. However, their limited capacity struggles with high-stakes legal reasoning tasks that require coherent statute interpretation and logically consistent deduction. Furthermore, training SLMs for such tasks demands high-quality, concise reasoning trajectories, which are prohibitively expensive to manually collect and difficult to curate via standard rejection sampling, which lacks granularity beyond final verdicts. To address these challenges, we propose LegalDrill, a diagnosis-driven synthesis framework that extracts and iteratively refines reasoning trajectories from a capable teacher via fine-grained prompting, then a self-reflective verification is employed to adaptively select the most effective data for the SLM student. The resulting data empower SLM training through supervised fine-tuning and direct preference optimization. Extensive experiments on several legal benchmarks demonstrate that LegalDrill significantly bolsters the legal reasoning capabilities of representative SLMs while bypassing the need for scarce expert annotations, paving a scalable path toward practical legal reasoning systems.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.15ACL Anthology · ACL 2026

Detecting AI-Generated Content on Social Media with Multi-modal Language Models

Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu 等 16 位作者

原文摘要

Generative AI has enabled the creation of photorealistic images and videos that are increasingly disseminated on social media, often used for spam, misinformation, manipulation, and fraud. Existing AI-generated content (AIGC) detection methods face challenges including poor generalization to new generation models, reliance on single modalities, and lack of interpretable explanations. We present our pipeline that mitigates these issues by continuously curating diverse multi-modal social media data and training a compact vision-language model for detection and explanation. Our model achieves state-of-the-art detection performance on public benchmarks and demonstrates robust detection and explanation capabilities on internal social media datasets across multiple platforms. We deployed our model for post recommendation on social media platforms and observed positive downstream impacts on user engagement, demonstrating that it is feasible to perform effective AIGC detection in dynamic, real-world social media environments.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.3ACL Anthology · ACL 2026

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He 等 59 位作者

原文摘要

We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1005ACL Anthology · ACL 2026

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

Wenhan Liu, Xinyu Ma Baidu, Weiwei Sun Carnegie Mellon University, Yutao Zhu, Yuchen Li Baidu Inc., Dawei Yin Baidu, Zhicheng Dou Renmin University of China

原文摘要

Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models (LRMs), many studies have demonstrated that step-by-step reasoning during test-time helps improve listwise ranking performance. However, due to the scarcity of reasoning-intensive training data, existing rerankers perform poorly in many complex ranking scenarios, and the ranking ability of reasoning-intensive rerankers remains largely underdeveloped. In this paper, we first propose an automated reasoning-intensive training data synthesis framework, which sources training queries and passages from diverse domains and applies DeepSeek-R1 to generate high-quality training labels. To empower the listwise reranker with strong reasoning ability, we further propose a two-stage training approach, which includes a cold-start supervised fine-tuning (SFT) stage and a reinforcement learning (RL) stage. During the RL stage, we design a novel multi-view ranking reward tailored to the multi-turn nature of listwise ranking. Extensive experiments demonstrate that our trained reasoning-intensive reranker ReasonRank outperforms existing baselines significantly and also achieves much lower latency than the pointwise reranker.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.104ACL Anthology · ACL 2026

Think in Sentences: Explicit Sentence Boundaries Enhance Language Model’s Capabilities

Zhichen Liu, Yongyuan Li, Yang Xu Southern University of Science and Technology

原文摘要

Researchers have explored ways to improve large language models (LLMs)’ capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but failed to leverage the inherent sentence-level structure of natural language. This is a critical oversight, as LLMs acquire linguistic capabilities through exposure to human-generated texts, which are inherently structured at the sentence level. Motivated by the gap, we proposed a method that inserts delimiters at sentence boundaries. Our method not only integrates dummy tokens into contexts, but also enables LLMs with sentence-by-sentence processing behavior during reasoning. Two approaches are proposed: (1). In-context learning and (2). Supervised fine-tuning are experimented from 7B LLMs to 600B Deepseek-V3. Experimental results demonstrate consistent improvements in various tasks, with notable gains of up to 7.7% on GSM8k and 12.5% on DROP. Furthermore, LLMs fine-tuned via our strategy further incorporate sentence awareness into their inner representations. Our work establishes a simple yet effective technique for enhancing LLM’s capabilities, offering promising directions for cognitive-inspired LLM enhancement paradigm.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1116ACL Anthology · ACL 2026

JanusMM: A Benchmark for Self-Deprecation Understanding in Real-World Multimodal Conversations

Xinyi Xu, Bingguang Hao ByteDance Inc., Yongyi Xiong, Zimo Chen University of Science and Technology of China, Xinchen Liu, Hongxin Guo, Xuelong Wang, Silin Zhou 等 9 位作者

原文摘要

Self-deprecation is a prevalent communicative strategy in human society, often using image-text interplay to express emotions and intentions. Despite self-deprecation is widespread in real-world conversations, the ability of multimodal large language models (MLLMs) to understand it remains underexplored. To fill this gap, we introduce JanusMM, the first benchmark designed to evaluate MLLMs’ understanding of self-deprecation in real-world conversations. JanusMM contains 2,016 bilingual memes from three types of social interactions and provides a dual-task evaluation framework with six new metrics. The first task assesses MLLMs’ abilities in self-deprecation recognition and reasoning, while the second task evaluates the consistency of their understanding by simulating the perspectives of the initiator and responder. We evaluate ten frontier MLLMs and find that they exhibit weak recognition and reasoning abilities, with their understanding of self-deprecation remaining inconsistent across both perspectives.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1305ACL Anthology · ACL 2026

Temporal Sampling for Forgotten Reasoning in LLMs

Yuetai Li, Zhangchen Xu, Fengqing Jiang Apple and University of Washington, Bhaskar Ramasubramanian Western Washington University, Luyao Niu University of Washington, Bill Yuchen Lin xAI and University of Washington, Xiang Yue Carnegie Mellon University, Radha Poovendran University of Washington, Seattle

原文摘要

Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term this phenomenon Temporal Forgetting and show that it is widespread across model sizes, fine-tuning methods (both Reinforcement Learning and Supervised Fine-Tuning), and multiple reasoning benchmarks. Our analysis reveals on average more than 20% of final errors were once solved correctly at an earlier checkpoint. Inspired by the phenomenon of Temporal Forgetting, we proposed Temporal Sampling, a simple decoding strategy that draws outputs from multiple checkpoints along the training trajectory. This approach recovers forgotten solutions and leads to significant improvements in reasoning performance than final-ckpt-sampling only, gains from 4 to 19 points in Pass@k and consistent gains for majority-voting and Best-of-N across several benchmarks. Temporal sampling also outperforms strong baselines such as model merging. By leveraging the temporal diversity inherent in training, Temporal Sampling offers a practical, compute-efficient way to surface hidden reasoning ability and rethink how we evaluate LLMs.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1335ACL Anthology · ACL 2026

Don’t Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction

Yuzhe Zhang Beijing University of Technology, Xianwei Xue, Xingyong Wu, Mengke Chen Baidu, Chen Liu Baidu, Xinran He, Run Shao, Feiran Liu College of Computer Science 等 11 位作者

原文摘要

Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency, rendering delays, and system interruptions, this assumption leads to undetected action failures, repetitive ineffective behaviors, and catastrophic error accumulation. Moreover, learning robust recovery strategies is challenging due to the high cost of online interaction and the lack of real-time feedback in offline datasets.We propose VeriGUI (Verification-driven GUI Agent), which explicitly models action outcomes and recovery under noisy environments. VeriGUI introduces a Thinking–Verification–Action–Expectation (TVAE) framework to detect failures and guide corrective reasoning, and a two-stage training pipeline that combines Robust SFT with synthetic failure trajectories and GRPO with asymmetric verification rewards. We further construct a Robustness Benchmark based on AndroidControl to evaluate failure recognition and correction. Experiments show that VeriGUI significantly reduces failure loops and improves recovery success while maintaining competitive standard task performance.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1427ACL Anthology · ACL 2026

UMPIRE: Unveiling LLM-generated Posts via Redundant Expressions

Xiaoquan Yi, Haixing Wu Wuhan University of Technology, Haozhao Wang, Yichen Li University of Cambridge, Mohamed bin Zayed University of Artificial Intelligence and Huazhong University of Science and Technology, Yuhua Li Huazhong University of Science and Technology, Rui Zhang Huazhong University of Science and Technology and Tsinghua University, Ruixuan Li Huazhong University of Science and Technology

原文摘要

The proliferation of Large Language Models (LLMs) has saturated social media platforms with hyper-realistic posts, rendering traditional detection methods that rely on low-level artifacts or unimodal statistics increasingly ineffective. In this work, we identify a fundamental semantic distinction: humans tend to complement visual content with additional context, while LLMs predominantly describe the visual information. To capture this, UMPIRE employs an orthogonal semantic decomposition mechanism that disentangles textual embeddings into redundant and complementary components. An adaptive gating module dynamically weighs these components to reflect diverse communicative styles. To enforce the desired geometric structure, we introduce a latent contrastive redundancy regularization loss that encourages LLM-generated content to exhibit high semantic redundancy, while human-written content emphasizes complementarity. Experimental results demonstrate that UMPIRE significantly outperforms state-of-the-art detection methods across multiple datasets, achieving up to a 5.38% improvement in accuracy.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1440ACL Anthology · ACL 2026

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing

Wenhao Yuan The University of Hong Kong,, Chenchen Lin, Jian Chen, Jinfeng Xu The University of Hong Kong, Xuehe Wang Sun Yat-sen Univerisity, Edith Cheuk-Han Ngai

原文摘要

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing unsupported beliefs repeatedly stored and propagated across decision steps, leading to systematic behavioral drift in long-horizon agentic systems. Most existing strategies rely on the consensus mechanism, conflating agreement with faithfulness. In this paper, inspired by the vulnerability of unfaithful intermediate reasoning trajectories, we propose Self-Audited Verified Reasoning (SAVeR), a novel framework that enforces verification over internal belief states within the agent before action commitment, achieving faithful reasoning. Concretely, we structurally generate persona-based diverse candidate beliefs for selection under a faithfulness-relevant structure space. To achieve reasoning faithfulness, we perform adversarial auditing to localize violations and repair through constraint-guided minimal interventions under verifiable acceptance criteria. Extensive experiments on six benchmark datasets demonstrate that our approach consistently improves reasoning faithfulness while preserving competitive end-task performance.

cs.CL · cs.AI

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1888ACL Anthology · ACL 2026

M^3-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering

Jiatong Ma Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Longteng Guo Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Yuchen Liu, Zijia Zhao, Dongze Hao, Xuanxu Lin Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Jing Liu Institute of automation, Chinese academy of science

原文摘要

We present M^3-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning. Unlike existing VQA datasets that focus on coarse-grained categories and simple reasoning over single entities, M^3-VQA introduces diverse multi-entity questions involving multiple distinct entities from both visual and textual sources. It requires models to perform both sequential and parallel multi-hop reasoning across multiple documents, supported by traceable, detailed evidence and a curated multimodal knowledge base. We evaluate 16 leading MLLMs under three settings: without external knowledge, with gold evidence, and with retrieval-augmented input. The poor results reveal significant challenges for MLLMs in knowledge acquisition and reasoning. Models perform poorly without external information but improve markedly when provided with precise evidence. Furthermore, reasoning-aware agentic retrieval surpasses heuristic methods, highlighting the importance of structured reasoning for complex multimodal understanding. M^3-VQA presents a more challenging evaluation for advancing the multimodal reasoning capabilities of MLLMs. Our code and dataset are available at https://github.com/CASIA-IVA-Lab/M3VQA.

cs.CL · cs.AI · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1963ACL Anthology · ACL 2026

HypoEval: Hypothesis-Guided Evaluation for Natural Language Generation

Mingxuan Li, Hanchen Li, Chenhao Tan University of Chicago

原文摘要

Large language models (LLMs) have demonstrated great potential for automating the evaluation of natural language generation. Previous frameworks of LLM-as-a-judge fall short in two ways: they either use zero-shot setting without consulting any human input, which leads to low alignment, or fine-tune LLMs on labeled data, which requires a non-trivial number of samples. Moreover, previous methods often provide little reasoning behind automated evaluations. In this paper, we propose HypoEval, Hypothesis-guided Evaluation framework, which first uses a small corpus of human evaluations to generate more detailed rubrics for human judgments and then incorporates a checklist-like approach to combine LLM’s assigned scores on each decomposed dimension to acquire overall scores. With only 30 human evaluations, HypoEval achieves state-of-the-art performance in alignment with both human rankings (Spearman correlation) and human scores (Pearson correlation), on average outperforming G-Eval by 11.86% and fine-tuned Llama-3.1-8B-Instruct with at least 3 times more human evaluations by 11.95%. Furthermore, we conduct systematic studies to assess the robustness of HypoEval, highlighting its effectiveness as a reliable and interpretable automated evaluation framework.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2084ACL Anthology · ACL 2026

Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory

Derong Xu City University of Hong Kong and University of Science and Technology of China, Shuochen Liu University of Science and Technology of China, Pengfei Luo, Pengyue Jia City University of Hong Kong, Yingyi Zhang, Yi Wen, Yimin Deng City University of Hong Kong and Xi'an Jiaotong University, Wenlin Zhang City University of Hong Kong 等 11 位作者

原文摘要

Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interactions. Existing memory systems mainly rely on static, hand-crafted update rules; although reinforcement learning (RL)-based agents learn memory updates, sparse outcome rewards provide weak supervision, resulting in unstable long-horizon optimization. Drawing on memory schema theory and the functional division between prefrontal regions and hippocampus regions, we introduce MemCoE, a cognition-inspired two-stage optimization framework that learns how memory should be organized and what information to update. In the first stage, we propose Memory Guideline Induction to optimize a global guideline via contrastive feedback interpreted as textual gradients; in the second stage, Guideline-Aligned Memory Policy Optimization uses the induced guideline to define structured process rewards and performs multi-turn RL to learn a guideline-following memory evolution policy. We evaluate on three personalization memory benchmarks, covering explicit and implicit preferences as well as different sizes and noise levels, and observe consistent improvements over strong baselines with favorable robustness, transferability, and efficiency[https://github.com/Applied-Machine-Learning-Lab/ACL2026_MemCoE].

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表