作者位次 #5/8ACL 2026Findings· Findings of ACL
Interactive Learning for LLM Reasoning
Hehai Lin · Shilei Cao · Sudong Wang · Haotian Wu · Minzhi Li · Linyi Yang · Juepeng Zheng · Chengwei Qin
摘要
Existing multi-agent learning approaches explicitly foster collaboration among Large Language Models (LLMs) to build stronger multi-agent systems (MAS), yet they still rely on re-executing the MAS during inference. This contrasts with human cognition, wherein individuals can internalize insights...