每日推送 · 2026年09月04日

📄 arXiv 论文	📕 小红书笔记
LLM Agent 2026-09-03 A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms Davide Paglieri, Logan Cross, Tim Genewein, Joel Z. Leibo, Nenad Tomasev 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
LLM Agent 2026-09-03 SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center Uday Vallabhaneni, Cassie L. Cagwin, David J. Wild 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
Agent Harness 2026-09-03 Environment Evolution for Terminal Agents Zhiyuan Fan, Tinghao Yu, Yuanjun Cai, Jiang Zhou, Jiangtao Guan 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
Long-Horizon Agent 2026-09-03 DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training Shubham Gandhi, Saurabh Goyal, Kiran Kate, Yara Rizk 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
LLM Agent 2026-09-03 Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting Muneeb Khan, Frederic Kirstein, Terry Ruas, Bela Gipp 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
Agent Harness 2026-09-03 A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors Pengxun Li, Litian Zhang, Jianwei Hou, Shujiang Wu, Song Li 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
Agent Harness 2026-09-03 Bioinfoysis Technical Report Qingyang Shao, Xin Zhang, Zhouyang Yuan, Xianying Chen, Yujia Xiang 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
Self-Evolving Agent 2026-09-03 SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic Simulation Qi Liu, Qinzheng Wang, Yiming Bie 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
Agent Harness 2026-09-03 What Do CAE Simulation Agents Really Need Beyond a Generic Harness? Jiasheng Shi, Tianhan Zhang 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—
LLM Agent 2026-09-03 KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents Yaxing Lyu, Shengjie Zhou, Binbin Toh, Pengyu Zhu, Lijun Li 💡 一句话总结（LLM 解析失败，请检查 API 响应） arXiv PDF	—

今日推送