2026
MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
ICLR 2026poster
Developing Large Language Models (LLMs) to cooperate and compete effectively within multi-agent systems (MASs) is a critical step towards more advanced intelligence. While reinforcement learning (RL) has proven effective for enhancing reasoning in single-agent tasks, its extension to multi-turn, mul…