Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning, high-quality long-chain reasoning data and optimized training pipelines still remain inadequately explored in vision-language tasks. In this paper, we present Insight-V, an early effort to 1) scalably produce long and robust reasoning data for complex multi-modal tasks, and 2) an effective training pipeline to enhance the reasoning capabilities of multi-modal large language models (MLLMs). Specifically, to create long and structured reasoning data without human labor, we design a two-step pipeline with a progressive strategy to generate sufficiently long and diverse reasoning paths and a multi-granularity assessment method to ensure data quality. We observe that directly supervising MLLMs with such long and complex reasoning data will not yield ideal reasoning ability. To tackle this problem, we design a multi-agent system consisting of a reasoning agent dedicated to performing long-chain reasoning and a summary agent trained to judge and summarize reasoning results. We further incorporate an iterative DPO algorithm to enhance the reasoning agent's generation stability and quality. Based on the popular LLaVA-NeXT model and our stronger base MLLM, we demonstrate significant performance gains across challenging multi-modal benchmarks requiring visual reasoning. Benefiting from our multi-agent system, Insight-V can also easily maintain or improve performance on perception-focused multi-modal tasks.
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
University of Electronic Science and Technology of China（电子科技大学）；Sun Yat-sen University（中山大学）；University of Washington（华盛顿大学）；Microsoft（微软公司）；The Chinese University of Hong Kong（香港中文大学）
本文提出覆盖数学、物理、化学和编程的 EMMA 多模态推理基准，揭示先进 MLLMs 在复杂跨模态、多步推理上仍存在明显不足。
Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；Sensetime Research（商汤科技研究院）；Beijing Institute of Technology（北京理工大学）；Shanghai AI Lab（上海人工智能实验室）
V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval
Tsinghua University（清华大学）；University of Central Florida（中央佛罗里达大学）；Fudan University（复旦大学）；The Australian National University（澳大利亚国立大学）；The University of Hong Kong（香港大学）；Pengcheng Laboratory（鹏城实验室）；Central South University（中南大学）
Tsinghua University（清华大学）；Meituan Inc（美团公司）；Central South University（中南大学）；Peking University（北京大学）；University of Chinese Academy of Sciences（中国科学院大学）；Nanyang Technological University（南洋理工大学）
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）；University of Washington（华盛顿大学）；Stanford University（斯坦福大学）；absolute AI；The Chinese University of Hong Kong（香港中文大学）
VL-Mamba: Exploring State Space Models for Multimodal Learning
Australian Institute for Machine Learning（澳大利亚机器学习研究所）；The University of Adelaide（阿德莱德大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models
Harvard Medical School, Harvard University（哈佛医学院、哈佛大学）；Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital（阿提尼乌拉A.马丁努斯生物医学成像中心、麻省总医院）；Knovel Engineering Lab, Singapore（Knovel工程实验室、新加坡）
EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability
Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China（计算机科学与技术系，人工智能研究院，清华大学，北京，中国）；Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China（人工智能产业研究院（AIR），清华大学，北京，中国）；School of Management, Fudan University, Shanghai, China（管理学院，复旦大学，上海，中国）
Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks
HKUST(GZ)（香港科技大学（广州））；HKUST（香港科技大学）；South China University of Technology（华南理工大学）；Shanghai Jiao Tong University（上海交通大学）；University of Pisa（比萨大学）；University of Trento（特伦托大学）
GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（基础模型研究中心，自动化研究所，中国科学院）；ByteDance（字节跳动）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）；Wuhan AI Research（武汉人工智能研究所）；Xi’an Jiaotong University（西安交通大学）；Renmin University of China（中国人民大学）
Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
Fudan University（复旦大学）；Alibaba Group Holding Limited（阿里巴巴集团控股有限公司）；Future Living Lab of Alibaba（阿里巴巴未来生活实验室）；University of Southern California（南加州大学）；Shanghai Innovation Institute（上海创新研究院）
Imagery as Inquiry: Exploring A Multimodal Dataset for Conversational Recommendation
University of California, San Diego（加利福尼亚大学圣迭戈分校）；Institute for Clarity in Documentation（文档清晰度研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗夸恩库尔特中心）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
Multimodal Video Emotion Recognition with Reliable Reasoning Priors
Lenovo Research（联想研究院）；School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院）；Institute of Automation, CAS（中国科学院自动化研究所）；Macau University of Science and Technology（澳门科学理工学院）；School of Computer Science and Technology, UCAS（中国科学院大学计算机科学与技术学院）
Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention
AMAP, Alibaba Group（阿里云实验室，阿里巴巴集团）；University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；Nanyang Technological University（南洋理工大学）
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所复杂系统认知与决策智能实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
University of Science and Technology of China（中国科学技术大学）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；iFLYTEK AI Research（iFLYTEK人工智能研究院）；Hong Kong University of Science and Technology（香港科学与技术大学）
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
Zhejiang University（浙江大学）；Fudan University（复旦大学）；Soochow University（苏州大学）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
College of Computer Science, Sichuan University, Chengdu, China（四川大学计算机学院）；National Key Laboratory of Fundamental Algorithms and Models for Engineering Simulation, Sichuan University, China（四川省工程仿真基础算法与模型国家重点实验室）
SciVQR: A Multidisciplinary Multimodal Benchmark for Advanced Scientific Reasoning Evaluation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；OPPO AI Center（OPPO AI中心）
MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences
Southeast University（东南大学）；Monash University（莫纳什大学）；Xiaohongshu Inc.（小红书）；Shanghai Jiao Tong University（上海交通大学）；University of Hong Kong（香港大学）；Zhejiang University（浙江大学）；Renmin University of China（中国人民大学）
