作者位次 #10/25ACL 2026Poster· Natural Language Processing
A gent G ym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
Zhiheng Xi · Dingwen Yang · Jiaqi Liu · Jixuan Huang · Honglin Guo · Baodai Huang · Tinggang Chen · Qi Zhang · Zhonghang Lu · Chenyu Liu · Jiajun Sun · Jiazheng Zhang · Dingwei Zhu · Xin Guo · Junzhe Wang · Zhihao Zhang · Yuming Yang · Junjie Ye · Minghe Gao · Dongrui Liu · Jiaming Ji · Guohao Li · Tao Gui · Qi Zhang · Xuanjing Huang
摘要
Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic evaluations. However, most existing benchmarks evaluate agents in simplified, idealized settings. They typically rely on...