CM2：基于集成多智能体框架的多模态文化推理
CM2: Multimodal Cultural Reasoning via an Integrated Multi-Agent Framework
浏览论文内容
中文总结 AI 辅助
针对多模态大语言模型（MLLM）跨学科文化推理不足的问题，提出基于人类文化解释认知路径的CM2多智能体框架，在CM2D数据集上较CoT等范式取得一致提升，各模块贡献及跨模态仲裁能力均得到验证。
中文摘要 AI 辅助
多模态大语言模型（MLLM）在STEM领域已取得显著成功，该领域的进展通常由相对稳定符号系统下的垂直逐步推导驱动。然而，它们在横向跨学科文化推理方面仍存在不足。本文提出CM2，一种基于人类文化解释认知路径的多智能体框架，CM2整合了多模态感知、检索增强生成、网络化推理、门控融合及奖励驱动机制。在CM2D数据集上，基于多种MLLM主干的实验显示，CM2相较于思维链（CoT）及典型推理范式取得了一致提升； ablation实验验证了各模块的贡献，冲突分析也证实了其真实的跨模态仲裁能力。
英文摘要
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.
发表机构
- Lanzhou University（兰州大学）
- Peking University（北京大学）
- Taiyuan University of Technology（太原理工大学）
机构由 AI 辅助整理，请以论文原文为准。
