作者位次 #11/13ICLR 2026Poster· Reinforcement Learning / Multi-agent
MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
Huining Yuan · Zelai Xu · Zheyue Tan · Xiangmin Yi · Mo Guang · Kaiwen Long · Haojia Hui · Boxun Li · Xinlei Chen · Bo Zhao · Xiao-Ping Zhang · Chao Yu · Yu Wang