mlsanityData to 14 Oct 2026

CM2: Multimodal Cultural Reasoning via an Integrated Multi-Agent Framework

arXiv 2608.30498 ↗First posted 31 Aug 2026cs.AIcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 2 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 12 of its 22 references that are in the map. First posted on arXiv 31 Aug 2026.

Builds on

12 of 22 references.

References · 12

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  6. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  8. 2026QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Modelscited by 7
  9. 2026SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answeringcited by 6
  10. 2026Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learningcited by 3
  11. 2026Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaborationcited by 3
  12. 2026When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detectioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries
  2. 2026A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications
  3. 2025A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation
  4. 2025Identity-Aware Large Language Models require Cultural Reasoning
  5. 2025Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning
  6. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
  7. 2025LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs
  8. 2025CulTrace: Tracing Internal Cultural Reasoning in Large Language Models