Integrating reasoning in large language models and large vision-language models has recently led to significant improvement of their capabilities. However, the generalization of reasoning models is still vaguely defined and poorly understood. In this work, we present an evaluation framework to rigorously examine how well chain-of-thought (CoT) approaches generalize on a simple planning task. Specifically, we consider a grid-based navigation task in which a model is provided with a map and must output a sequence of moves that guides a player from a start position to a goal while avoiding obstacles. The versatility of the task and its data allows us to fine-tune model variants using different input representations (visual and textual) and CoT reasoning strategies, and systematically evaluate them under both in-distribution (ID) and out-of-distribution (OOD) test conditions. Our experiments show that, while CoT reasoning improves in-distribution generalization across all representations, out-of-distribution generalization (e.g., to larger maps) remains very limited in most cases when controlling for trivial matches with the ID data. Surprisingly, we find that reasoning traces which combine multiple text formats yield the best (and non-trivial) OOD generalization. Finally, purely text-based models consistently outperform those utilizing image-based inputs, including a recently proposed approach relying on latent space reasoning.
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。
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）
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）
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）
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）
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）
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）
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）
Learning to Reason About Implicit Multimodal Harm: From Diagnosis to Generalization
Max Planck Institute for Informatics（马克斯·普朗克院信息研究所）；Saarland Informatics Campus（萨尔兰州信息校园）；Saarland University（萨尔兰州大学）；The University of Edinburgh（爱丁堡大学）；Samsung AI Center, Cambridge（三星AI中心，剑桥）
Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection
School of Computer Science and Engineering（计算机科学与工程学院）；Key Laboratory of Computer Network and Information Integration (SEU), Ministry of Education（计算机网络与信息集成重点实验室（SEU））
