跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 15:29 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 16:00 — 2026-11-09 16:00（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：2026-11-09 15:29最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 5 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 15:27（北京时间）
新论文 · v1arXiv:2611.03575

VeriHarm-Bench: Measuring Harmful Success in LLM Coding Agents Verifiably

Wei-Lin Chen, Zhepei Wei, Xinyu Zhu, Yu-Min Tseng, Tzu-Han Lin, Yu Meng

原文摘要

Large language model (LLM) coding agents increasingly operate with shell access, allowing them to write scripts, move files, alter permissions, and modify system configurations. However, an agent may achieve a user's goal while causing unintended harm, such as deleting unrelated files, weakening access controls, or corrupting data, in response to benign inputs without explicit jailbreaking. This failure mode is particularly important because apparent task success may reassure users that an agent behaved correctly, causing harmful side effects to go unnoticed. We call this harmful success: the agent successfully completes the intended benign task while simultaneously causing unintended harm. Despite its importance, harmful success is difficult to measure because conventional task-success metrics overlook harmful behaviors, while existing safety evaluations are often designed solely to assess harmful outcomes. We introduce VeriHarm, an automatic framework for constructing programmatically verifiable benchmarks that directly measure harmful success. VeriHarm minimally perturbs coding tasks to elicit unintended harmful behavior while maintaining the benignity of the task and preserving the original task objective. It then synthesizes executable harm tests that, together with the original task-correctness tests, evaluate both task accuracy and harmful outcomes. Frontier agents, including GPT-5.6-Sol and Claude-Opus-5, achieve an average task accuracy of 95% on our curated VeriHarm-Bench, yet still struggle to complete tasks safely: their safe success rate, the fraction of tasks completed successfully without triggering the designated harm, averages only 37%. These results suggest that successful task completion can frequently coexist with unintended harm, and that task-success metrics alone may substantially understate the potential safety risks of coding agents.

cs.CL · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03223

Do Agents Still Follow the Rules? Benchmarking Rule Compliance under Agent Context Compaction

Yiwei Zha, Qingyu Meng, Herbert Bos, Min Chen

原文摘要

LLM agents compact long histories to fit their context windows, but the compacted context must still carry the operating rules that govern later actions. Prior work shows that violations rise after compaction, but measures compliance outside a complete agent harness and does not identify where each violation comes from. We introduce ARCBench(Agent Rule Compliance Benchmark), a configurable benchmark built on the open-source pi agent harness. Its tool-calling agent loop lets us measure rule compliance from actions taken during execution, bringing the evaluation closer to deployed agent workflows. Using ARCBench, we examine where violations after compaction come from, and how different compaction configurations and adversarial settings change their sources. We find that compaction rarely deletes the rule: most violations after compaction occur while the rule is still in the compacted history, with the agent treating a later request as permission, ignoring the rule, and proceeding anyway. Where violations come from depends on the configuration: how the rule is delivered decides whether the agent would break it even without compaction, while the compaction strategy and budget decide whether the rule survives. The strongest compactor-targeted attack more than doubles violations by corrupting the rule in the summary and changing how the agents behave, whereas the strongest defense restores the rule in most summary but still violates. Finally, retaining a rule does not guarantee compliance: compacted runs that retain the rule violate more than twice as often as runs with the full history.

cs.CR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1595ACL Anthology · ACL 2026

Aligning Large Language Models via Fully Self-Synthetic Data

Shangjian Yin University of California, Riverside, Zhepei Wei University of Virginia, Xinyu Zhu University of Virginia, Charlottesville, Wei-Lin Chen University of Virginia, Charlottesville, Yu Meng University of Virginia

原文摘要

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses, often necessitating external reward models or proprietary models like GPT-4 to annotate preference pairs. In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment, where all training data, including prompts (i.e., user queries), responses, and preferences, are generated by the model itself. Specifically, SAO first instructs the LLM to engage in persona role-play and generate diverse prompts and responses, which are then self-evaluated for preference optimization. Extensive experiments demonstrate that SAO effectively enhances the model’s chat capabilities on standard benchmarks like AlpacaEval 2.0, while maintaining strong performance on downstream objective tasks (i.e.,, question-answering, math reasoning). Our work provides a practical solution for self-improvement in aligning LLMs, and the code for reproducing our results is available at: https://github.com/SJY8460/SAO.

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.1842ACL Anthology · ACL 2026

PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference

Hao Zhang, Lyu Mengsi, Zhuo Chen Beijing Academy of Artificial Intelligence, Yulong Ao Beijing Academy of Artificial Intelligence, Yonghua Lin

原文摘要

Large Language Models (LLMs) demonstrate exceptional capabilities across various tasks, but their deployment is constrained by high computational and memory costs. Model pruning provides an effective means to alleviate these demands. However, existing methods often ignore the characteristics of prefill-decode (PD) disaggregation in practice. In this paper, we propose a pruning method that is highly integrated with PD disaggregation, enabling more precise pruning of blocks. Our approach constructs pruning and distillation sets to perform iterative block removal, obtaining better pruning solutions. Moreover, we analyze the pruning sensitivity of the prefill and decode stages and identify removable blocks specific to each stage, making it well suited for PD disaggregation deployment. Extensive experiments demonstrate our approach consistently achieves strong performance in both PD disaggregation and PD unified (non-PD disaggregation) settings, and can also be extended to other non-block pruning methods. Under the same settings, our method achieves improved performance and faster inference.

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

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