作者位次 #6/8ACL 2026Findings· Findings of ACL
FAER : Benchmarking VLM s for Failure-Aware Embodied Reasoning
Hao Song · Kaifeng Liu · Yuanxing Liu · Xiang Tian · Xuesong Wang · Chen Yifan · Weinan Zhang · Ting Liu
摘要
Failures are inevitable when embodied agents execute complex tasks. Visual-language models (VLMs) serve as the core component of embodied agents in perceiving the environment and making decisions. Assessing the capabilities of VLMs in detecting and reasoning about failures has become increasingly...