mlsanityData to 14 Oct 2026

RVLM: Recursive Vision-Language Models with Adaptive Depth

arXiv 2603.24224 ↗First posted 25 Mar 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Medical AI systems face two fundamental limitations. First, conventional vision-language models (VLMs) perform single-pass inference, yielding black-box predictions that cannot be audited or explained in clinical terms. Second, iterative reasoning systems that expose intermediate steps rely on fixed iteration budgets wasting compute on simple cases while providing insufficient depth for complex ones. We address both limitations with a unified framework. RVLM replaces single-pass inference with an iterative generate-execute loop: at each step, the model writes Python code, invokes vision sub-agents, manipulates images, and accumulates evidence. Every diagnostic claim is grounded in executable code, satisfying auditability requirements of clinical AI governance frameworks. RRouter makes iteration depth adaptive: a lightweight controller predicts the optimal budget from task-complexity features, then monitors progress and terminates early when reasoning stalls. We evaluate on BraTS 2023 Meningioma (brain MRI) and MIMIC-CXR (chest X-ray) using Gemini 2.5 Flash without fine-tuning. Across repeated runs, RVLM shows high consistency on salient findings (e.g., mass presence and enhancement) and can detect cross-modal discrepancies between Fluid-Attenuated Inversion Recovery (FLAIR) signal characteristics and segmentation boundaries. On MIMIC-CXR, it generates structured reports and correctly recognises view-specific artefacts. Code: https://github.com/nican2018/rvlm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 20 of its 38 references that are in the map. First posted on arXiv 25 Mar 2026.

Builds on

20 of 38 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023MAIRA-1: A specialised large multimodal model for radiology report generation22 Nov
  2. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day1 Jun

Other references · 18

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  4. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  5. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  6. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  7. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  8. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 384
  9. 2020Generating Radiology Reports via Memory-driven Transformercited by 368
  10. 2024Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoningcited by 280
  11. 2024Mixture-of-Depths: Dynamically allocating compute in transformer-based language modelscited by 258
  12. 2017On the Automatic Generation of Medical Imaging Reportscited by 216
6 more
  1. 2021PonderNet: Learning to Pondercited by 168
  2. 2020Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generationcited by 141
  3. 2020The Right Tool for the Job: Matching Model and Instance Complexitiescited by 126
  4. 2024THREAD: Thinking Deeper with Recursive Spawningcited by 25
  5. 2025LADDER: Self-Improving LLMs Through Recursive Problem Decompositioncited by 25
  6. 2024Visual Program Distillation with Template-Based Augmentationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
  2. 2025Think Twice to See More: Iterative Visual Reasoning in Medical VLMs
  3. 2026Route, Retrieve, Reflect, Repair: Self-Improving Agentic Framework for Visual Detection and Linguistic Reasoning in Medical Imaging
  4. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
  5. 2025RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints
  6. 2025Can Generalist Vision Language Models (VLMs) Rival Specialist Medical VLMs? Benchmarking and Strategic Insights
  7. 2025How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study
  8. 2026When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models