mlsanityData to 14 Oct 2026

Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents

arXiv 2510.18424 ↗First posted 21 Oct 2025cs.AIcited by 1

On the map: LLM reasoning → Clinical and biomedical applications

also in 2 more
Abstract (arXiv)

Visual Language Models (VLMs) achieve promising results in medical reasoning but struggle with hallucinations, vague descriptions, inconsistent logic and poor localization. To address this, we propose a agent framework named Medical Visual Reasoning Agent (Med-VRAgent). The approach is based on Visual Guidance and Self-Reward paradigms and Monte Carlo Tree Search (MCTS). By combining the Visual Guidance with tree search, Med-VRAgent improves the medical visual reasoning capabilities of VLMs. We use the trajectories collected by Med-VRAgent as feedback to further improve the performance by fine-tuning the VLMs with the proximal policy optimization (PPO) objective. Experiments on multiple medical VQA benchmarks demonstrate that our method outperforms existing approaches.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 53 of its 69 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

53 of 69 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs1 Apr
  2. 2025FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training16 Jan
  3. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning16 Nov
  4. 2022Can large language models reason about medical questions?17 Jul

Other references · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  8. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  9. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  10. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  11. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  12. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
37 more
  1. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  3. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  4. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  5. 2017Billion-scale similarity search with GPUscited by 2,497
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  7. 2024A Survey on LLM-as-a-Judgecited by 1,423
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  9. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  10. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  11. 2019Publicly Available Clinical BERT Embeddingscited by 1,002
  12. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 733
  13. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 688
  14. 2024Self-Rewarding Language Modelscited by 681
  15. 2019MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographscited by 597
  16. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 478
  17. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 388
  18. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 376
  19. 2024Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoningcited by 280
  20. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 196
  21. 2023Emergent autonomous scientific research capabilities of large language modelscited by 132
  22. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 97
  23. 2024GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AIcited by 96
  24. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Modelscited by 85
  25. 2023Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillingscited by 69
  26. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Modelscited by 64
  27. 2024RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Modelscited by 60
  28. 2023A Systematic Evaluation of GPT-4V's Multimodal Capability for Medical Image Analysiscited by 37
  29. 2024GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaborationcited by 34
  30. 2024HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wildcited by 27
  31. 2024Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generationcited by 23
  32. 2024MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimizationcited by 21
  33. 2017R3: Reinforced Reader-Ranker for Open-Domain Question Answeringcited by 9
  34. 2025Medical large language models are easily distractedcited by 9
  35. 2025Guiding Medical Vision-Language Models with Explicit Visual Prompts: Framework Design and Comprehensive Exploration of Prompt Variationscited by 7
  36. 2024Visual Prompt Engineering for Vision Language Models in Radiologycited by 6
  37. 2025Exploring Interpretability for Visual Prompt Tuning with Cross-layer Conceptscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learningcited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2026MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning
  2. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
  3. 2025Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
  4. 2026CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
  5. 2026Inference-Time Agentic Decision Rules Beat Longer Evolving Search for Multi-Image Medical Reasoning
  6. 2025UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-Making
  7. 2025AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering
  8. 2025Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA