COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning
LEMON (Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning), an LLM-based orchestrator that learns to design efficient multi-agent orchestration while improving the accuracy-token trade-off.
Xudong Chen, Yixin Liu, Hua Wei et al.
· 0 citations