用多智能体模拟人类文化推理，提升跨模态理解能力
CM2: Multimodal Cultural Reasoning via an Integrated Multi-Agent Framework
- 构建多智能体框架，模仿人类文化理解的认知路径
- 在多个模型上实现超越思维链的跨模态推理性能
- 适合研究跨文化多模态推理与智能体协作的学者
多模态大语言模型在科学、技术、工程和数学领域表现优异，这些领域通常依赖稳定符号系统下的垂直推导。然而，其在横向、跨学科的文化推理方面仍待深入探索。我们提出CM2，一种基于人类文化解释认知路径的多智能体框架，集成多模态感知、检索增强生成、网络化推理、门控融合与奖励驱动反馈。在涵盖多个MLLM基线的CM2D数据集上的实验表明，该框架在各项指标上持续优于CoT及典型推理范式；消融实验验证了各模块的有效性，冲突分析进一步证实了跨模态仲裁的真实性。
原文摘要 · Abstract (English)
Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deduction under relatively stable symbol systems. Their horizontal, interdisciplinary cultural reasoning, however, remains underexplored.We propose CM2, a multi-agent framework grounded in the cognitive pathway of human cultural interpretation. CM2 integrates multimodal perception, retrieval-augmented generation, networked reasoning, gated fusion, and reward-driven feedback.Experiments on CM2D across multiple MLLM backbones show consistent gains over CoT and typical reasoning paradigms; ablations validate each module's contribution, and conflict analyses confirm genuine cross-modal arbitration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。