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

+1865新增论文
+1473其中 AI 相关
+176已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 17:12各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 19:13 — 2026-11-17 19:13(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:2026-11-17 04:58最近发现新增版本:2026-11-17 17:12库内论文最新更新时间:2026-11-17 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。

25,692 已收录论文21,414 AI 相关7,613 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 21 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.21072

Sage S2.1 Flash Technical Report

Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng, Xu Dai, Guanting Dong, Qiming Ge, Lixin Gu 等 206 位作者

原文摘要

We introduce Sage S1.5 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S1.5 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench~2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench~II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.

cs.AI

新论文 · v1arXiv:2611.14364

ARE-bench:在真实研究者会话与工作区中评测智能体的研究能力

ARE-bench: Benchmarking Agents' Research Ability in Real-World Researcher Sessions and Workspaces

Jiahang Lin, Wanying Ren, Wanghan Xu, Huayu Sha, Yang Shu, Zhonghang Lu, Chengjun Pan, Yi Dong 等 27 位作者

AI 速读 基于摘要

ARE-bench 用真实研究者的会话与未清理工作区构建 75 个任务,检验研究智能体能否在延续项目时遵守先前决策与工作区状态。

cs.CL

查看原文摘要

Research agents achieve increasingly strong benchmark scores, yet these scores do not necessarily translate into reliable delivery in ongoing research projects. Many research-agent benchmarks emphasize standalone tasks and relatively self-contained workflows in clean or curated workspaces. However, researchers ask agents to complete one step within an ongoing project, where requests depend on earlier session decisions and workspaces contain unfinished files, outdated versions, and failed attempts. We introduce ARE-bench to evaluate whether research agents advance ongoing projects while respecting prior decisions and existing workspace state, grounded in real session context and in-progress workspaces. ARE-bench includes 75 tasks built on agent sessions and full workspaces from recruited researchers' own projects, spanning seven research stages, 33 requirements, and 150 sub-requirements, with 1,173 binary checklist items in total. Each task is anchored at a real user request, preserves its requirements, and summarizes the earlier requests still in effect as background. The complete workspace is replayed to that boundary without cleanup, preserving artifacts from earlier turns. Each checklist is compiled from an intent-aligned rubric and credits any valid solution. Across seven frontier models, the strongest passes every checklist item on only 66.2% of tasks, and Design and Execution rank among the hardest stages for every model. Three models pass about 69% of tasks when only delivery contracts and general norms are checked, but just 28.4% to 40.0% once historical and material or workspace requirements are also checked. Evaluating delivery without these contextual requirements can therefore overestimate research agents and mask differences between them.

新论文 · v1arXiv:2611.10404

Coding or Cheating? An Investigation of Frontier Coding LLMs

Yuntao Gui

原文摘要

Frontier agentic LLMs are trained on verifiable rewards in reinforcement learning (RL) environments built from real software repositories. A passing test suite is treated as the reward for solving the task. We show that, on hard problems, frontier models often satisfy these rewards by obtaining the answer instead of deriving it, known as reward hacking. Prior reports document this behavior on public benchmarks. We test its persistence on unseen problems. In a hardened environment where the answer cannot leak, nearly every model we tested attempted to recover the answer, escalating through tiers of increasingly specialized exploitation: mining the repository history for the upstream fix, inspecting the git object store directly, and sweeping the filesystem for a possible newer copy of the source or hidden tests. These attempts were concentrated on the hardest problems, and the models differed in whether, how often, and how deeply they escalated. Our position is that this behavior is a learned shortcut, acquired in RL environments that leak the answer, not a sign of intelligence. We release agent traces for these models to support further study at https://huggingface.co/datasets/logitly-ai/reward-hacking-raw-v1.

cs.CL · cs.AI

新论文 · v1arXiv:2611.05036

ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents

Guanting Dong, Zhichao Sun, Xinyu Yang, Rui Wang, Xin Deng, Jiajie Jin, Zhixiong Yang, Junhao Huang 等 25 位作者

原文摘要

Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they first synthesize a database and scenario, then derive tools and tasks from them. As a result, tool interfaces may not match real ones, tool compositions are not grounded in execution, and tasks rarely span more than one environment. We propose ToolSpace, a tool-centric framework that reverses this order. ToolSpace mines data, state, and retry dependencies from adjacent calls in execution traces of real MCP services and open agent corpora, using deterministic rules rather than LLM judgment, and clusters the resulting weighted tool-composition graph into environments. Databases are synthesized only for state-mutating environments, while query and stateless tools replay recorded returns. ToolSpace then performs state-aware random walks with rollback and decompiles each chain into a natural-language task with assertion-based checks, keeping only samples that replay successfully from the initial state. Applied to AutomationBench and tau3-Bench Banking, the pipeline produces harder Pro versions on which 7 frontier models drop by up to 38.2 points. Across seven long-horizon tool-use benchmarks, ToolSpace raises Qwen3.6-35B-A3B from 23.0 to 41.0 average score (43.2 with RL) and GLM-5.2 from 44.6 to 56.6, on par with Claude Opus 5. Ablations show that execution-witnessed edges clearly outperform LLM-judged ones, and performance keeps improving with data and environment scale.

cs.CL

新论文 · v1arXiv:2611.03178

CoworkOS:Scaling Agent Coworkers for Real-world Automation

Jiajie Jin, Guanting Dong, Chengjun Pan, Xin Deng, Zhuohui Sheng, Guoqiang Wang, Tao Gui, Yutao Zhu 等 40 位作者

原文摘要

Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and decision-making over long horizons, a combination that remains an open challenge. We introduce CoworkOS, a general-purpose harness for long-horizon work that separates task strategy from execution management: the model decides actions, delegation, and acceptance, while the runtime maintains state and feedback. Its three-layer architecture enables direct execution or delegation to Subagents, synchronously or asynchronously, under stable responsibilities. Through a shared application layer, humans and agents inspect and revise the same evolving documents, presentations, CAD models, and Blender scenes, so human-in-the-loop participation can enter both through conversation and through direct modification of the work itself. To sustain continuity across agents and sessions, CoworkOS further introduces hierarchical workspaces and persistent semantic memory, so working files, key decisions, and long-running Job logs remain shareable, reusable, and resumable after interruption. Across 12 benchmarks and 6 categories of real-world applications, CoworkOS proves highly competitive with frontier agent applications such as Codex and DeepSeek Harness. As a sustained-work case study, CoworkOS uses GLM-5.3 as its backbone to conduct RSI-driven automated post-training on Qwen3.6-35B-A3B. Over five rounds, the model's average score across eight benchmarks rose from 33.19 to 42.95 (+9.76). Looking ahead, we believe CoworkOS opens a meaningful path toward general cowork-agent intelligence.

cs.AI · cs.CL

版本更新 · v2arXiv:2609.11234

NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment

Guoqiang Zhang, Kexin Tan, Ming Zhang, Li Ju, Wenqing Jing, Zhonghan Yue, Jiayi Chen, Shiqiang Wu 等 15 位作者

原文摘要

Large language models (LLMs) are increasingly used in peer review at major AI conferences, yet novelty remains a persistent weak point. Existing benchmarks assess novelty as a single holistic score, making it difficult to diagnose which dimension a model misjudges or whether its evidence is faithful. We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis. The benchmark contains 619 paper pairs and 50 multi-paper sets, drawn from two expert sources: ICLR reviewer overlap claims and survey co-citations. Instances are independently labeled along three dimensions: task, problem, and method, capturing application goals, technical challenges, and solution approaches. We propose a cascading diagnostic pipeline that verifies per-dimension correctness, evidence grounding, and logical support. Evaluation of 18 LLMs shows hallucination rates ranging from 0% to 39% across dimensions, and among non-hallucinated correct-positive judgments, over 70% cite evidence fails to logically support the stated reason. The best-performing model, GPT-5.5, achieves 43-72% Verified F1 across dimensions, while most models retain less than half of their raw F1 after faithfulness verification. These results suggest that current LLMs remain far from reliable scientific novelty assessment, particularly when correctness is conditioned on faithful evidence grounding.

cs.AI

版本更新 · v3arXiv:2606.14867

Evaluating the Robustness of Proof Autoformalization in Lean 4

Zhengtao Gui, Sheng Yang, Zhouxing Shi

原文摘要

Proof autoformalization aims to translate a mathematical informal proof in natural language into a formal proof in a formal language such as Lean 4. Existing LLM-based models for proof autoformalization are typically evaluated only on well-formed informal proofs from curated datasets. We argue that a robust proof autoformalizer must remain faithful even for informal proofs that diverge from these idealized ones, and we present the first study on the robustness of proof autoformalization models. We formulate two categories of perturbations: a global perturbation paraphrases the informal theorem-proof pair in a different style, under which the formalization should remain consistent; a local perturbation alters a value, symbol, or proof step, possibly in a counterfactual way, and a robust formalization should faithfully reflect the perturbation rather than reverting to the original or inferring a different one on its own. We build a benchmark with both perturbations on miniF2F and MATH-500, and automatically measure how stable a proof autoformalization's correctness is under global perturbations and how faithfully its output reflects local perturbations. We evaluate seven recent models: their correctness varies under global perturbations, and they mostly fail to remain faithful under local perturbations.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2610.25752

Which Answers Agree? Evaluating Self-Consistency from Incomplete Logs

Zhengtao Gui, Zexi Chen, Weining Shen

原文摘要

Self-consistency answers a question by generating multiple responses and selecting the most frequent answer. Its evaluation requires both correctness labels and information about which responses agree; correctness labels alone generally determine neither voting accuracy nor the benefit of additional votes. For tasks in which all correct responses map to the same normalized answer, we derive sharp accuracy bounds using classical stochastic majorization, refined by abstention counts and answer-category limits. We also derive sharp bounds on accuracy changes across voting budgets that share a response pool. When answer-category counts are available, we introduce Plurality-U, a count-based dynamic program that exactly averages voting accuracy over all fixed-size subsets, eliminating finite-pool Monte Carlo error. On 1,403,520 stored outputs from recent reasoning models in Scorio Lite and Scorio Trace, recording abstention counts and answer options cuts the width of SuperGPQA accuracy intervals by more than half. For moving from 9 to 17 votes, our bounds reduce interval width by a median of 77.7% on SuperGPQA and 72.3% on 14 GPQA and Adaptive-Consistency pools, compared with a baseline that combines separate accuracy bounds. Exact computation has lower paired median runtime than 2,000-subset Monte Carlo in 14 of 15 tested pool-budget settings. These results clarify what incomplete logs can establish and provide an exact evaluation procedure when answer counts are retained.

cs.LG

新论文 · v1arXiv:2610.38282

Human Evaluation with Automatic Scores: Separating Sampling and Estimation Gains

Yang Liu, Ran Zou, Zhengtao Gui, Chao Xue

原文摘要

Automatic judges offer inexpensive information about model outputs, but an evaluation team must decide how to turn that information into fewer human annotations. Scores can guide sampling, correct an estimate, or support adaptive acquisition, and these uses may capture overlapping gains. We compare their incremental value on fixed evaluation pools from three preference datasets, and 19 attributed-question-answering systems. Matched comparisons use the same scores, account for pilot labels and budget rules, and separate acquisition from estimation. Score stratification is a strong reference: after ten-bin stratification, the best fixed local linear correction offers only 1.00--5.27% further MSE reduction in the primary configurations. Unequal allocation offers larger gains in some pools, but can increase error when confident scores conceal variable human outcomes. Comparison on AttributedQA, shrinking learned quotas toward score-only quotas lowers pooled MSE for 17 of 19 systems relative to the score-only procedure, but ordinary pooled 95% intervals cover only 88.09--93.54%. The same shrinkage improves on the score-only reference in only one of eight preference configurations. Ranking experiments further show that lower individual MSE need not improve system selection. These findings support a simple starting procedure, proportional sampling within score strata followed by a stratified human mean, and identify what additional evidence is needed to justify correction or adaptation for the intended evaluation output.

cs.CL

版本更新 · v2arXiv:2609.35290

EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning

Shihan Dou, Shaofan Liu, Zhonghang Lu, Jiahang Lin, Shichun Liu, Binghai Wang, Jiajie Jin, Guanting Dong 等 11 位作者

原文摘要

Recent work has explored improving agents by jointly evolving their harnesses and models, but often takes a ''potpourri'' approach that bundles together new tools, new decision-making procedures, and model adaptation to the evolved harness under a single notion of agent improvement. In this paper, we instead investigate how agents can improve their decision-making procedures. In particular, we propose EvoIn, an agent fine-tuning framework that bridges evolution and internalization. EvoIn first analyzes agent execution traces to evolve and validate new decision-making procedures by temporarily instantiating them in the harness. The validated procedures guide the agent to generate improved reasoning traces. These traces are then rewritten into self-contained reasoning traces, removing explicit references to harness instructions while expressing the induced decision logic as the model's own reasoning. Finally, EvoIn fine-tunes the model on the rewritten traces, internalizing these procedures so that the improved decision-making persists without the evolved harness at inference time. We evaluate EvoIn on diverse benchmarks and find that it consistently enables agents to learn stronger decision-making procedures, raising the pass rate by 10.9 points in-domain and by 9.2 points out-of-domain. Results further show that the internalized decision procedures generalize to unseen tasks. Case studies show that agents can learn to decide how to solve a task before solving it, for example by checking a document's length to choose between reading it in full and searching it. EvoIn is also broadly applicable, showing consistent improvements on another model family.

cs.AI · cs.CL

版本更新 · v5arXiv:2610.04906

Scaling Verifiable Environments for Long-horizon Work Agents

Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei, Yajie Yang, Chenyang Liao, Enyu Zhou 等 26 位作者

原文摘要

Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons.

cs.CL · cs.AI

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1010ACL Anthology · ACL 2026

Counteracting the Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing

Xin Guo, Zhiheng Xi, Yiwen Ding, Yitao Zhai Meituan, Xiaowei Shi, Xunliang Cai Meituan, Tao Gui Fudan University, Qi Zhang Fudan University 等 9 位作者

原文摘要

Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision–language models (LVLMs), where models explore and learn from successful trajectories iteratively. However, we identify a critical imbalance during this process: the model readily generates high-quality trajectories for simple queries (i.e., head data) but struggles with complex ones (i.e., tail data). This bias drives the optimization to disproportionately prioritize simple reasoning skills, while inhibiting the acquisition of complex capabilities. As iterations progress, this imbalance becomes more acute—a dynamic we term the “Matthew effect”, ultimately stalling performance gains. To mitigate this, we approach head-tail re-balance during the exploration-and-learning process from two perspectives: distribution-reshaping and trajectory-resampling. Extensive experiments on Qwen2-VL-7B-Instruct and InternVL2.5-4B models across visual reasoning tasks demonstrate that our methods consistently improve visual reasoning capabilities, outperforming vanilla self-improvement baselines by an average of 3.86 points.

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.1103ACL Anthology · ACL 2026

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai 等 19 位作者

原文摘要

Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete reward supervision, which undermines policy stability and generalization. Such noise may cause models to ignore key information or even collapse in advantage estimation. We find that a strong value model is essential for absorbing unstable signals and producing reliable advantages, offering denser and more robust supervision than the reward model. To better optimize noisy supervision, we propose VRPO, a framework that enhances value modeling for robust RL in LLM post-training. VRPO integrates (1) auxiliary losses guided by entropy and perplexity from a frozen language model, and (2) a variational information bottleneck, enabling the value model to filter noise and capture key words. This design allows the value model to correct noise rewards and generate more reliable advantage estimates, transforming it from a passive predictor into an active noise regulator. Experiments on multi-turn dialogue, math reasoning, and science QA with both rule-based and model-based rewards show that VRPO consistently outperforms baselines such as PPO and GRPO. Our work highlight the central role of the value model in Robust RL and provide a principled and practical approach to policy optimization under noisy supervision.

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.1214ACL Anthology · ACL 2026

Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training

Changhao Jiang, Ming Zhang Fudan University, Yifei Cao Fudan University, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun Fudan University 等 15 位作者

原文摘要

The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the capacity of a pre-trained language model to memorize factual information from its corpus, and introduce a principled method to estimate it prior to training. We propose Size-dependent Mutual Information (SMI), an information-theoretic predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering (QA) accuracy. SMI is validated through large-scale document retrieval over the disclosed pre-training corpora of 21 public and 3 custom models, combined with a robust multi-template QA evaluation. Experiments show that SMI significantly outperforms repetition-based baselines and achieves R² > 0.7 in predicting QA accuracy for models above 1B parameters, without additional training. The analysis further reveals diminishing returns from scaling data and model size and provides evidence for an intrinsic upper bound on knowledge retention achievable by pre-training alone, motivating retrieval and other augmentation strategies.

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.1462ACL Anthology · ACL 2026

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization

Junzhe Wang, Zhiheng Xi, Yajie Yang, Hao Luo, Shihan Dou, Tao Gui Fudan University, Qi Zhang Fudan University

原文摘要

Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavailable during pretraining. While reinforcement learning has been widely adopted for training such agents, existing approaches face key limitations: process supervision often suffers from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards. To bridge this gap, we propose Contribution-Weighted GRPO (CW-GRPO), a framework that integrates process supervision into group relative policy optimization. Instead of directly optimizing process rewards, CW-GRPO employs an LLM judge to assess the retrieval utility and reasoning correctness at each search round, producing per-round contribution weights. These weights are used to rescale outcome-based advantages along the trajectory, enabling fine-grained credit assignment without sacrificing optimization stability. Experiments on multiple knowledge-intensive benchmarks show that CW-GRPO outperforms standard GRPO by 5.0% on Qwen3-8B and 6.3% on Qwen3-1.7B, leading to more effective search behaviors. Additional analysis reveals that successful trajectories exhibit concentrated contributions in specific rounds, providing empirical insight into search agent tasks. Our code is available at https://github.com/zsxmwjz/CW-GRPO.

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.1839ACL Anthology · ACL 2026

DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data

Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou Fudan University, Junjie Ye, Shaowen Wang, Shichun Liu 等 12 位作者

原文摘要

Reward models (RMs) are the surrogate objectives in reinforcement learning from human feedback (RLHF), and their scores directly steer policy optimization. We show that standard RM training is vulnerable in data subsets where response quality depends only weakly on the context: such instances encourage the RM to ignore the context, leading to context neglect and degraded accuracy. To address this failure mode, we propose Distribution-Aware Reward Modeling (DARM), which augments the RM objective with a conditional mutual information regularizer that maximizes context and the predicted reward conditioned on the response. By explicitly preserving the sensitivity of reward signals to the prompting context, DARM reduces over-reliance on response-only features and improves robustness to contextual variation. Extensive experiments across in-distribution and out-of-distribution settings show that DARM trained RMs deliver more accurate and consistent scoring than strong baselines. We further evaluate its downstream impact in RLHF, where DARM produce better aligned policies. We also demonstrate the necessity of each DARM design component and the impact of key parameters on performance through ablation experiments.

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.1924ACL Anthology · ACL 2026

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models

Binghai Wang, Yantao Liu Qwen Team, Alibaba Group, Yuxuan Liu Qwen Team, Alibaba Group, Tianyi Tang Alibaba Group, Shenzhi Wang Alibaba Group, Chang Gao Alibaba Group, Chujie Zheng Alibaba Group, Yichang Zhang Alibaba Group 等 16 位作者

原文摘要

Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy, which undermines their ability to generalize during RLHF. We introduce Rationale Consistency, a fine-grained metric that quantifies the alignment between the model’s reasoning process and human judgment. Our evaluation of frontier models reveals that rationale consistency effectively discriminates among state-of-the-art models and detects deceptive alignment, while outcome accuracy falls short in both respects. To mitigate this gap, we introduce a hybrid signal that combines rationale consistency with outcome accuracy for GenRM training. Our training method achieves state-of-the-art performance on RM-Bench (87.1%) and JudgeBench (82%), surpassing outcome-only baselines by an average of 5%. Using RM during RLHF, our method effectively improves performance as demonstrated on Arena Hard v2, notably yielding a 7% improvement in creative writing tasks. Further analysis confirms that our method escapes the deceptive alignment trap, effectively reversing the decline in rationale consistency observed in outcome-only training.

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.1950ACL Anthology · ACL 2026

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Yuming Yang Fudan University, Mingyoung Lai University of Toronto, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao 等 16 位作者

原文摘要

Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show that trajectories from stronger teachers do not necessarily yield better students, highlighting the importance of data-student suitability in distillation. Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model’s current behavior but overlooking more informative ones. Addressing this, we propose Rank–Surprisal Ratio (RSR), a simple metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory. RSR is motivated by the observation that effective trajectories typically balance learning signal strength and behavioral alignment by combining low absolute probability with relatively high-ranked tokens under the student model.Concretely, RSR is defined as the ratio of a trajectory’s average token-wise rank to its average negative log-likelihood, and is straightforward to compute and interpret. Across five student models and reasoning trajectories from 11 diverse teachers, RSR strongly correlates with post-training reasoning performance (average Spearman 0.86), consistently outperforming existing metrics. We further demonstrate its practical utility in both trajectory selection and teacher selection.

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.2058ACL Anthology · ACL 2026

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang Fudan University, Honglin Guo Fudan University, Baodai Huang, Tinggang Chen, Qi Zhang 等 25 位作者

原文摘要

Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic evaluations. However, most existing benchmarks evaluate agents in simplified, idealized settings. They typically rely on pre-packaged tool interfaces, overlook critical steps, and assume inputs are clean and fully specified. Consequently, they understate the difficulty of real deployments, where uncertainty and noise are ubiquitous and agents must proactively explore the environment to uncover new tools. To bridge this gap, we present AgentGym2, a new evaluation framework with task instances grounded in real-world end-to-end working demands. Beyond reasoning and planning, it measures agents’ ability to execute end-to-end procedures, discover tools via exploration, compose tools for unseen tasks, and remain robust to noisy and underspecified information. Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2, revealing a substantial gap between the capability of current agents and the demands of real-world applications.

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.269ACL Anthology · ACL 2026

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding

Deming Ding Large Language Model Algorithm Engineer, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo Fudan University, Weiyu Cheng Minimax Ai 等 15 位作者

原文摘要

Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are heterogeneous and persist across interactions. To fill this gap, we introduce OctoBench, which benchmarks scaffold-aware instruction following in repository-grounded agentic coding. OctoBench includes 34 environments and 217 tasks instantiated under three scaffold types, and is paired with 7,098 objective checklist items. To disentangle solving the task from following the rules, we provide an automated observation-and-scoring toolkit that captures full trajectories and performs fine-grained checks. Experiments on eight representative models reveal a systematic gap between task-solving and scaffold-aware compliance, underscoring the need for training and evaluation that explicitly targets heterogeneous instruction following. We will release the benchmark to support reproducible benchmarking and to accelerate the development of more scaffold-aware coding agents.

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.972ACL Anthology · ACL 2026

LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models

Ming Zhang Fudan University, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan The University of Tokyo, The University of Tokyo and Fudan University, Qiyuan Peng, Yue Zhang ATOM INFINITE PTE. LTD. 等 22 位作者

原文摘要

Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting, critical issues that obscure true model capabilities. To address this, we introduce LLMEval-Fair, a framework for dynamic evaluation of LLMs. LLMEval-Fair is built on a proprietary bank of 220k graduate-level questions, from which it dynamically samples unseen test sets for each evaluation run. Its automated pipeline ensures integrity via contamination-resistant data curation, a novel anti-cheating architecture, and a calibrated LLM-as-a-judge process achieving 90% agreement with human experts, complemented by a relative ranking system for fair comparison. An 30-month longitudinal study of nearly 60 leading models reveals a performance ceiling on knowledge memorization and exposes data contamination vulnerabilities undetectable by static benchmarks. The framework demonstrates exceptional robustness in ranking stability and consistency, providing strong empirical validation for the dynamic evaluation paradigm. LLMEval-Fair offers a robust and credible methodology for assessing the true capabilities of LLMs beyond leaderboard scores, promoting the development of more trustworthy evaluation standards.

cs.CL

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