AI RESEARCH
End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
arXiv CS.LG
•
ArXi:2506.02718v2 Announce Type: replace 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 equipped with search tools, mitigate these issues via task decomposition and retrieval-augmented problem solving.