AI RESEARCH

Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy

arXiv CS.AI

ArXi:2603.06801v1 Announce Type: new Multi-Agent Debate (MAD) has emerged as a promising paradigm for enhancing large language model reasoning. However, recent work reveals a limitation:standard MAD cannot improve belief correctness beyond majority voting; we refer to this as the Martingale Curse. This curse arises because correlated errors cause agents to converge toward erroneous consensus, where debate merely reinforces collective mistakes rather than filtering noise.