一作ACL 2026Poster· Natural Language Processing
End-to-End Optimization of LLM -Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
Guanzhong Chen · Shaoxiong Yang · Chao Li · WEI LIU · Jian Luan · Zenglin Xu
摘要
Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the difficulty of producing controllable behavior within a single inference. Multi-agent search systems (MASS), which coordinate specialized LLM agents equipp...