#claude-code

Claude Code

2 articles

arXivAI Safety

LLM Agents Can Easily Tamper with Their Own Traces: A Critical Security Flaw in Agent Frameworks

LLM Agent 可輕易篡改自身執行軌跡：現行代理框架的重大安全漏洞

Researchers reveal that popular LLM agent frameworks fail to protect execution traces from being tampered with or deleted by the agents themselves, posing significant risks for compliance and safety monitoring.

Sep 25, 20262 min read

arXivRobotics

Coding Agents Outperform Hand-Engineered Planners in Task and Motion Planning

程式碼生成 Agent 突破機器人規劃瓶頸：自動編寫高泛化性的 TAMP 解決方案

Researchers demonstrate that coding agents can interactively synthesize highly generalizable programs for task and motion planning (TAMP), achieving up to 95% success and outperforming hand-engineered baselines.

Sep 25, 20262 min read