Identifying the Risks of LM Agents with an LM-Emulated SandboxYangjun Ruan,Honghua Dong,Andrew Wang,Silviu Pitis,Yongchao Zhou,Jimmy Ba,Yann Dubois,Chris J. Maddison,Tatsunori HashimotoICLR 2024（2024）引用 108|浏览455关键词Language Model Agent,Tool Use,Evaluation,Safety,Language ModelAI 理解论文溯源树样例生成溯源树，研究论文发展脉络Chat Paper正在生成论文摘要
