让下一篇重要论文，不再错过。

新论文 · v1arXiv:2611.10156

更新于 2026-11-07

DeepResearch RewardBench: Evaluating Reward Models for Deep Research Report

Shudong Liu, Yuting Zhong, Guanhua Chen, Xinyi Yang, Junnan Liu, Lidia S. Chao, Jiaheng Liu, Derek F. Wong

原文摘要

Empowered by Large Language Models (LLMs), deep research systems integrate online information into research reports through multi-step web searching and information synthesis. Evaluating these reports presents a significant challenge due to their long context, high information density, and domain specificity, necessitating the use of AI evaluation as a substitute for prohibitively expensive human assessment. However, few studies have examined the effectiveness of existing reward models or LLMs in understanding and evaluating such research reports. To bridge this gap, we introduce DeepResearch RewardBench, the first benchmark dedicated to evaluating reward modeling for research reports. We collect diverse report candidates from multiple agents or tool-augmented LLMs. These candidates are scored using query-specific golden rubrics, and we ensure data quality and difficulty through a combination of multi-round filtering and human verification. Our benchmark comprises preference datasets formatted as pairs, triplets, and quadruplets to test ranking capabilities across varying levels of difficulty. Extensive experiments demonstrate that while current reward models handle general coherence effectively, their performance significantly degrades when evaluating research reports. Generative LLMs acting as judges demonstrate comprehensive superiority in this domain, with comparative evaluation proving more effective than direct scoring methods. We anticipate that this benchmark will serve as a vital testbed for the evaluation and advancement of research agents.

cs.AI · cs.CL

新论文 · v1arXiv:2611.03509

更新于 2026-11-03

Attacking P2P Networks: Liveness Attacks on the GossipSub and DOG Gossip Protocols

Jiaheng Li, Anton Paramonov, Yann Vonlanthen

原文摘要

Peer-to-peer (P2P) networks form the communication layer of large decentralized systems such as Ethereum, and the correctness of higher-level protocols depends on the gossip layer delivering messages to honest nodes. We study the robustness of two gossip protocols against adversaries whose only goal is to violate liveness, that is, to prevent honest nodes from receiving fresh messages, without forging, altering, or invalidating any message. For GossipSub, the publish-subscribe protocol used by Ethereum, we show that an adversary operating a constant number of geographically distributed nodes with a fixed latency advantage can take over the ``First Message Deliveries'' peer-scoring term and separate a constant fraction of nodes from the honest mesh. We analyze the attack under a geographical model, address the random-peer and outbound-connection mechanisms, and show that the separation can be maintained under realistic churn. For DOG, a transaction-dissemination protocol designed for CometBFT, we first give simple counterexamples in which route filtering disconnects the dissemination graph even without failures or Byzantine participants, and then present a practical attack that uses only a single physical node with a constant number of identities and legitimate actions to disable every forwarding route, separating the full network while allowing only direct publisher-to-neighbor delivery. We verify the attack in a simulated network and analyze its cost, assumptions, and possible mitigations.

cs.CR

新论文 · v1arXiv:2610.37341HF 社区推荐

更新于 2026-10-27

CodeCap-Bench: Can Code Serve as a Good Video Caption?

Jiafu Tang, Yifan Xu, Eric Tang, Junjie Zhao, Shipeng Luo, Te Sun, Haoxuan Hu, Yiyan Ji 等 14 位作者

原文摘要

Video captioning aims to preserve visual information through compact descriptions, predominantly using natural language. However, precisely expressing fine-grained spatial structures and temporal dynamics in natural language often leads to lengthy and potentially ambiguous descriptions. In this work, we explore Code as Video Caption, a paradigm where executable programs serve as a complementary representation of visual content through graphical primitives, layout rules, and functions of time. To examine whether code captions effectively preserve video information, we compare them with natural language captions on downstream question answering and video reconstruction tasks. Our results show that code captions achieve superior reasoning accuracy and reconstruction fidelity. Despite these advantages, realizing the potential of code captioning depends on whether current multimodal large language models (MLLMs) can generate faithful code captions. To systematically assess this capability, we introduce CodeCap-Bench, which comprises 323 videos spanning five categories of structured 2D content, along with fine-grained annotations and a multi-level evaluation framework. Extensive experiments reveal that while leading proprietary MLLMs demonstrate promising code captioning capabilities, they still struggle to faithfully capture complex temporal dynamics, with open-source models lagging substantially behind.

cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1167ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding

Yuhang Li, Chenchen Zhang, Ruilin Lv, Ao Liu Tencent, Ken Deng, Yuanxing Zhang Kuaishou- 快手科技, Jiaheng Liu Nanjing University, Bo Zhou

原文摘要

While Large Language Models (LLMs) excel at algorithmic code generation, they struggle with front-end development, where correctness is judged on rendered pixels and interaction. We present ReLook, an agentic, vision-grounded reinforcement learning framework that empowers an agent to close a robust generate–diagnose–refine loop by invoking a multimodal LLM (MLLM) as a tool. During training, the agent employs an MLLM-in-the-loop to serve as a visual critic, evaluating code via screenshots and providing actionable feedback. Crucially, we enforce a strict zero-reward policy for invalid renders to guarantee renderability and mitigate reward hacking. To prevent behavioral collapse, we introduce Forced Optimization, a strict acceptance rule that admits only improving revisions, yielding monotonically better trajectories. At inference, we decouple the critic and run a lightweight, critic-free self-edit cycle, keeping latency comparable to base decoding while retaining most of the gains. Across three widely used benchmarks, ReLook consistently outperforms strong baselines in vision-grounded front-end code generation, highlighting the benefits of agentic perception, visual rewards, and training–inference decoupling.

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.139ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization

Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang Princeton University 等 19 位作者

原文摘要

Translating natural language mathematical statements into formal, executable code is a fundamental challenge in automated theorem proving. While prior work has focused on generation and compilation success, little attention has been paid to the critic phase—the evaluation of whether generated formalizations truly capture the semantic intent of the original problem. In this paper, we introduce CriticLean, a novel critic-guided reinforcement learning framework that elevates the role of the critic from a passive validator to an active learning component. Specifically, first, we propose the CriticLeanGPT, trained via supervised fine-tuning and reinforcement learning, to rigorously assess the semantic fidelity of Lean 4 formalizations. Then, we introduce CriticLeanBench, a benchmark designed to measure models’ ability to distinguish semantically correct from incorrect formalizations, and demonstrate that our trained CriticLeanGPT models can significantly outperform strong open- and closed-source baselines. Building on the CriticLean framework, we construct FineLeanCorpus, a dataset comprising over 509K problems that exhibits rich domain diversity, broad difficulty coverage, and high correctness based on human evaluation.Overall, our findings highlight that optimizing the critic phase is essential for producing reliable formalizations and we hope our CriticLean will provide valuable insights for future advances in formal mathematical reasoning.

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.2122ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning

Siyuan Gan, Jiaheng Liu Nanjing University, Boyan Wang nanjing university, Tianpei Yang Nanjing University, Runqing Miao China Mobile Communications Company Limited Research Institute, Yuyao Zhang China Mobile Communications Company Limited Research Institute, Fanyu Meng JIUTIAN Research, Junlan Feng 等 11 位作者

原文摘要

Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (CoT), which significantly increase computational overhead. To address this overthinking problem, existing work focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. Unfortunately, using RL will suffer the the reward hacking problem, e.g., the model engages in thinking but is judged as not doing so, resulting in incorrect rewards.To mitigate this problem, existing works either employ supervised fine-tuning (SFT), which incurs high computational costs, or enforce uniform token limits on non-thinking responses, which yields limited mitigation of the problem.In this paper, we propose Thinking-Based Non-Thinking (TNT). It does not employ SFT, and sets different maximum token usage for responses not using thinking across various queries by leveraging information from the solution component of the responses using thinking. Experiments on five mathematical benchmarks demonstrate that TNT reduces token usage by around 50\\%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5B, while significantly improving accuracy. In fact, TNT achieves the optimal trade-off between accuracy and efficiency among all tested methods. Additionally, the probability of reward hacking problem in TNT’s responses, which are classified as not using thinking, remains below $10\\%$ across all tested datasets.

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.478ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors

Chenghao Yang, Yuning Zhang, Zhoufutu Wen, Tao Gong University of Science and Technology of China, Jiaheng Liu Nanjing University, Qi Chu University of Science and Technology of China, Nenghai Yu University of Science and Technology of China

原文摘要

Model distillation is a primary driver behind the rapid progress of LLM agents, yet it often leads to behavioral homogenization. Many emerging agents share nearly identical reasoning steps and failure modes, suggesting they may be distilled echoes of a few dominant teachers. Existing metrics, however, fail to distinguish mandatory behaviors required for task success from non-mandatory patterns thatreflect a model’s autonomous preferences. We propose two complementary metrics to isolate non-mandatory behavioral patterns: \textbf{Response Pattern Similarity (RPS)} for verbal alignment and \textbf{Action Graph Similarity (AGS)} for tool-use habits modeled as directed graphs. Evaluating 18 models from 8 providers on \tau-Bench and \tau^2-Bench against Claude Sonnet 4.5 (thinking), we find that within-family model pairs score 5.9 pp higher in AGS than cross-family pairs, and that Kimi-K2 (thinking) reaches 82.6% S_{\text{node}} and 94.7% S_{\text{dep}}, exceeding Anthropic’s own Opus 4.1. A controlled distillation experiment further confirms that AGS distinguishes teacher-specific convergence from general improvement. RPS and AGS capture distinct behavioral dimensions (Pearson r = 0.491), providing complementary diagnostic signals for behavioral convergence in the agent ecosystem.Our code is available at https://github.com/Syuchin/AgentEcho.

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.970ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS

Baolin Zheng Alibaba Group, Guanlin Chen Alibaba Group, Qingyang Teng Alibaba Group, Hongqiong Zhong, Yingshui Tan Alibaba Group, Zhendong Liu, Weixun Wang Alibaba Group, Jiaheng Liu Nanjing University 等 15 位作者

原文摘要

Despite their rapid advancement, Multimodal Large Language Models (MLLMs) remain vulnerable to diverse safety risks. Current benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale, and the oversight of complex modality combinations (e.g., cross-modal risks). To address this, we introduce the Unified Safety Benchmark (USB), a comprehensive framework covering 61 risk categories across four distinct modality interactions. We first demonstrate that existing benchmarks—even when aggregated—leave significant coverage gaps. To bridge this, we design a sophisticated data synthesis pipeline that generates complementary data, ensuring balanced coverage across all risk dimensions. Furthermore, beyond evaluating vulnerability to harmful queries, USB incorporates the simultaneous assessment of model over-refusal on benign inputs as an integrated diagnostic suite. Experimental results, evaluating 22 MLLMs across 244 risk-modality intersections, demonstrate that existing MLLMs still struggle with the trade-off between avoiding vulnerabilities and over-refusal. Models are particularly vulnerable to image-only or cross-modal risky inputs, highlighting the persistent need for refined safety mechanisms. Warning: This paper contains unfiltered and potentially harmful content that may be offensive.

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