Overview

Multimodal reasoning studies how models perceive information across modalities, connect that evidence to knowledge, and use it to answer questions, plan actions, or explain decisions. Common approaches include instruction tuning and chain-of-thought training, reinforcement learning with verifiable rewards, tool-using agents, and structured methods such as graphs or symbolic solvers. Benchmarks such as MathVista and MMMU test visual problem solving, while video, document, scientific, and medical tasks probe reasoning across time and specialized evidence. A central challenge is ensuring that correct answers actually depend on relevant multimodal evidence rather than language shortcuts; grounding, cross-modal integration, and reliable generalization remain difficult.

Latest papers

CardsList

531 papers29 papers in the last four weeks, down 44% on the four weeks before. 0.2% of all new papers.

  1. PRISM: A Category-Theoretic Framework for Measuring and Refining Multimodal Analogies

    Oct 1, 2026Mirella Zeisler, Ojas Shirekar, Mircea Licǎ +1Cross-Modal AlignmentMultimodal Reasoning

  2. MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning

    Oct 1, 2026Juekai Lin, Honglin Lin, Yuqian Yuan +7Reinforcement LearningMultimodal Reasoning

  3. ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

    Oct 1, 2026Bingchen Pei, Lichong Chen, Bingxi Zhao +8Multimodal QAMultimodal Reasoning

  4. OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

    Sep 30, 2026Junming Lin, Yuxuan Wang, Zhenxin Lei +11On-Policy Self-DistillationMultimodal Reasoning

  5. From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement Learning

    Sep 30, 2026Jialu Pi, Yanan Ma, Weijie Chen +8Clinical Outcome PredictionMultimodal Reasoning

  6. OmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells

    Sep 29, 2026Manyu Li, Xunkai Li, Yongfu Xiong +3Visual Question AnsweringMultimodal Reasoning

  7. LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation

    Sep 29, 2026Jaeyun Shin, Hangeol Chang, Jong Chul YeVLM DistillationMulti-Teacher Knowledge Distillation

  8. DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning

    Sep 29, 2026Cheng Ye, Weidong Chen, Bingyan Xu +1VLM RobustnessMultimodal Reasoning

  9. ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language Models

    Sep 29, 2026Ruochen Zhang, Yao Huang, Yitong Sun +5Multimodal ReasoningLLM Safety

  10. Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models

    Sep 28, 2026Ross Callaghan, Niannu Gao, Hojjat Azadbakht +1Multimodal ReasoningMultimodal Model Evaluation

  11. V-Gym: Enhancing Agentic Visual Reasoning via Skill-Data Co-Evolution

    Sep 28, 2026Bei Yan, Yuecong Min, Jie Zhang +3Synthetic Data GenerationMultimodal Reasoning

  12. IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection

    Sep 27, 2026Hongwei Niu, Yunpeng Luo, Hanjun Li +6AI-Generated Text DetectionMultimodal Large Language Models

  13. VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings

    Sep 27, 2026Peixi Wu, Mingzhou Jiang, Feipeng Ma +11Multimodal IREfficient Multimodal Inference

  14. OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation

    Sep 27, 2026Jingchen Ni, Yuji Wang, Shannan Yan +3Unified Multimodal ModelsReferring Video Object Segmentation

  15. PhysAlign: A Benchmark for Evidence-Grounded Role Alignment in Multimodal Physics Reasoning

    Sep 27, 2026Kecheng Liang, Haoyang Liu, Zexin Chen +5Multimodal GroundingMultimodal Reasoning

  16. EngIntervene: Benchmarking Multimodal Engineering State Understanding and Design Intervention Reasoning

    Sep 27, 2026Jinchang Zhang, Yingda Tao, Jiakai Lin +1Multimodal GroundingMultimodal Reasoning

  17. CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models

    Sep 26, 2026Long Qian, Bingke Zhu, Jiaqi Wei +3Diffusion VLMsVision-Language Models

  18. MM-OPD: Towards One More Bottleneck Between Perception and Reasoning

    Sep 26, 2026Jintao Tong, Yujing Lou, Zhanming Shen +6Multimodal Large Language ModelsMultimodal Reasoning

  19. OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents

    Sep 26, 2026Jihoo Jung, Suho Yoo, Jeongsoo Choi +5Multimodal AgentsMultimodal Reasoning

  20. RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning

    Sep 26, 2026Ziqiao Shang, Zian Xu, Ji-Chen Yan +6LLM Agent Skill LearningAgent Skill Learning

  21. RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation

    Sep 26, 2026Qilang Ye, Meng Liu, Yu ZhouAudio-Visual NavigationEmbodied Navigation

  22. Multimodal Thinking with Renderable Programs

    Sep 24, 2026Sunli Chen, Ding Zhong, Ziqiao Ma +6Multimodal ReasoningVLM Reasoning

  23. Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration

    Sep 24, 2026Jiaqi Deng, Zonghan Wu, Zhan Heng +3Multimodal GroundingMultimodal Large Language Models

  24. Pistis Technical Report

    Sep 23, 2026Heyun Chen, Xiaohan Lan, Jiaxi Li +17Multimodal Large Language ModelsMultimodal Reasoning

  25. Cognitive Action Reasoning for Proactive Robots from Human-Centered Multimodal Observations

    Sep 20, 2026Zhihao Gu, Kechao Zhu, Yuanfeng Wu +7Multimodal ReasoningHuman-Robot Interaction

  26. AniPrO: Interpretable Anime Image Provenance Detection via Multi-Dimensional Semantic Reasoning

    Sep 20, 2026Yan Liu, Baoxiang Huang, Zi'an Wang +1AI-Generated Image DetectionDigital Image Forensics

  27. FireWorldBench: Benchmarking Complex Physical World Intelligence through Coupled-Field Fire Dynamics

    Sep 19, 2026Qiang Chen, Hao Guo, Huatai Zhu +7Physical ReasoningAI Agent Benchmarks

  28. DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning

    Sep 18, 2026Wan Xu, Yuanfan Guo, Kevin Han +2Multimodal ReasoningMultimodal CoT Reasoning