AI RESEARCH
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
arXiv CS.CL
•
ArXi:2605.02801v1 Announce Type: new As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studies RL for LLM-based multi-agent systems through orchestration traces: temporal interaction graphs whose events include sub-agent spawning, delegation, communication, tool use, return, aggregation, and stopping decisions. Using this lens, we identify three technical axes.