GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
GAM-Agent:面向复杂视觉推理的博弈论与感知不确定性感知协作框架
专题命中 视觉推理 :VLM(summary_cn,abstract);visual reasoning(title);分类 cs.AI
AI总结 该研究提出GAM-Agent博弈论多智能体框架,通过基础感知智能体与关键验证智能体的非零和博弈及不确定性感知协作,在四个视觉推理基准上显著提升了中小及强规模VLM的性能,为可靠可解释多模态推理提供了新路径。
Comments Accepted at NeurIPS 2025. Code available at https://github.com/jushengzhang/Gam-Agent