多智能体辩论为何失效？这篇论文系统分析失败条件，挑战你对AI协作的固有认知。
arXiv:2510.20963v2 Announce Type: replace Abstract: Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multipl…
用Wald的序贯概率比检验动态调控LLM辩论轮数，显著提升推理效率与资源利用率
arXiv:2605.19193v1 Announce Type: new Abstract: Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, o…
通过自我辩论预训练推理模型，让AI学会多智能体辩论的新方法，思路清奇且极具研究价值。
arXiv:2601.22297v2 Announce Type: replace Abstract: The reasoning abilities of large language models (LLMs) have been substantially improved by reinfo…