作者位次 #2/7ACL 2026Findings· Findings of ACL
FAMA : Failure-Aware Meta-Agentic Framework for Open-Source LLM s in Interactive Tool Use Environments
Amir Saeidi · Venkatesh Mishra · Souradeep Mukhopadhyay · Gaowen Liu · Ali Payani · Jayanth Srinivasa · Chitta Baral
摘要
Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue resolution scenarios, these agents frequently fail due t...