#llm
4 articles
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.
RAPID：只需單次視覺示範，AI 代理即可自動生成與優化機器人操控程式
RAPID is a framework that automatically infers task specifications and environments from a single visual demonstration, using an agentic loop to program and refine generalized robot skills.
不需重新訓練！PoEM 演算法直接預測新獎勵函數的強化學習結果
The PoEM framework enables researchers to accurately predict and synthesize new RL policies without any actual RL training, by leveraging linear combinations of existing post-trained models in log-space.
自動漏洞修復的指標迷思：為何「編譯率」與 CodeBLEU 無法真實反映 LLM 的修復能力
A study reveals that 'compile rate' and CodeBLEU fail as metrics for LLM-based vulnerability repair, often rewarding non-repairs, and proposes diff_F1 as a reliable, change-aware filtering alternative.