RL for VLMs

RL: Reinforcement Learning · VLM: Vision-Language Model

Overview

This field studies how reinforcement learning can improve models that interpret images or video alongside language, and sometimes take actions in visual environments. Common approaches include group-relative policy optimization, PPO, and reinforcement learning from verifiable rewards, with feedback based on answer correctness, visual evidence, intermediate reasoning, preferences, or tool use. Applications range from image and video question answering, spatial reasoning, and medical analysis to navigation and robotic manipulation. A central challenge is ensuring that better scores reflect genuine use of visual evidence rather than language shortcuts, while designing reliable rewards and efficient training that generalize beyond the training setting.

Latest papers

CardsList

507 papers39 papers in the last four weeks, down 43% on the four weeks before. 0.3% of all new papers.

  1. NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning

    Feb 24, 2026Ishaan Rawal, Shubh Gupta, Yihan Hu +1Vision-Language-Action ModelsAutonomous Driving

  2. PyVision-RL: Forging Open Agentic Vision Models via RL

    Feb 24, 2026Shitian Zhao, Shaoheng Lin, Ming Li +4Adaptive Video Frame SamplingMultimodal Agents

  3. Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning

    Feb 22, 2026Zhuoxu Huang, Mengxi Jia, Hao Sun +2RL ExplorationRL for VLMs

  4. GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking

    Feb 19, 2026Zixu Cheng, Da Li, Jian Hu +4Video SGGVideo Reasoning

  5. TikArt: Stabilizing Aperture-Guided Fine-Grained Visual Reasoning with Reinforcement Learning

    Feb 16, 2026Hao Ding, Zhichuan Yang, Weijie Ge +3VLM ReasoningMultimodal Reasoning

  6. WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

    Feb 15, 2026Zhennan Jiang, Shangqing Zhou, Yutong Jiang +11World Models for RoboticsWorld Models

  7. Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models

    Feb 13, 2026Liangzhi Shi, Shuaihang Chen, Feng Gao +8VLA TrainingSim-to-Real Transfer

  8. LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation

    Feb 12, 2026Yue Hu, Avery Xi, Qixin Xiao +4Robot NavigationVision-Language Navigation

  9. Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs

    Feb 9, 2026Siqu Ou, Tianrui Wan, Zhiyuan Zhao +2Reasoning for VLMsAttention Intervention in VLMs

  10. Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification

    Jan 23, 2026Zongwan Cao, Bingbing Wen, Lucy Lu WangVisual Question AnsweringActive Visual Question Answering

  11. Think3D: Thinking with Space for Spatial Reasoning

    Jan 19, 2026Zaibin Zhang, Yuhan Wu, Lianjie Jia +103D Spatial ReasoningVLM Reasoning

  12. CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation

    Jan 12, 2026Chaoyu Li, Fei Tao, Pooyan FazliTest-Time Scaling for VLMsTest-Time Scaling

  13. HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize

    Jan 6, 2026Kun Zhao, Guodong Liu, Hui Ji +7Radiology Report GenerationMedical VLMs

  14. Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design

    Jan 1, 2026Omar Sharif, Eftekhar Hossain, Nikhil Singh +1Reasoning for VLMsVision-Language Models

  15. From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme

    Dec 31, 2025Xueyan Li, Yingyi Xue, Mengjie Jiang +2VLM ReasoningRL for VLMs

  16. Skin-R1: Clinical Knowledge-Guided Dermatological Diagnosis Using Vision-Language Models

    Nov 18, 2025Zehao Liu, Weijieying Ren, Jipeng Zhang +4VLM RobustnessMedical Diagnosis

  17. SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

    Nov 10, 2025Hunar Batra, Haoqin Tu, Hardy Chen +3Multimodal UnderstandingScene Graph Generation

  18. On the Faithfulness of Visual Thinking: Measurement and Enhancement

    Oct 27, 2025Zujing Liu, Junwen Pan, Qi She +2Faithfulness in VLMsMultimodal CoT Reasoning

  19. Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models

    Oct 11, 2025Mingyang Lyu, Yinqian Sun, Erliang Lin +4Flow MatchingRobotic Manipulation

  20. Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback

    Oct 2, 2025Derek Shi, Ruben Glatt, Christine Klymko +5Video-Language ModelsRL Fine-Tuning

  21. AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving

    Sep 17, 2025Yuechen Luo, Fang Li, Shaoqing Xu +11Autonomous DrivingReasoning for VLAs

  22. Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning

    Aug 22, 2025Ruiqi Wu, Yuang Yao, Na Su +11RL for VLMsMedical Image Analysis

  23. AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization

    Aug 6, 2025Jingyi Liao, Yongyi Su, Rong-Cheng Tu +6VLM AdaptationIndustrial Anomaly Detection

  24. VRPRM: Process Reward Modeling via Visual Reasoning

    Aug 5, 2025Xinquan Chen, Chongying Yue, Bangwei Liu +3Process Reward ModelsMultimodal Reward Modeling

  25. Multimodal Mathematical Reasoning with Diverse Solving Perspective

    Jul 3, 2025Wenhao Shi, Zhiqiang Hu, Yi Bin +4Multimodal ReasoningMultimodal CoT Reasoning