作者位次 #4/10ICML 2026Poster· Reinforcement Learning / Multi-agent
Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
Dan Qiao · Binbin Chen · Fengyu Cai · Jianlong Chen · Wenhao Li · Fuxin Jiang · Zuzhi Chen · Hongyuan Zha · Tieying Zhang · Baoxiang Wang