作者位次 #7/8ACL 2026Findings· Findings of ACL
S afety ALFRED : Evaluating Safety-Conscious Planning of Vision Language Models
Josue Torres-Fonseca · Naihao Deng · Yinpei Dai · Shane Storks · Yichi Zhang · Rada Mihalcea · Casey Kennington · Joyce Chai
摘要
Multimodal Large Language Models (MLLMs) are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insufficient. We introduce SafetyALFRED, built upon the embodied agent benchmark ALFRED, augmented with six categorie...