mlsanityData to 14 Oct 2026

Rule-Based Reinforcement Learning for Document Image Classification with Vision Language Models

arXiv 2509.22283 ↗First posted 26 Sep 2025cs.CVcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Rule-based reinforcement learning has been gaining popularity ever since DeepSeek-R1 has demonstrated its success through simple verifiable rewards. In the domain of document analysis, reinforcement learning is not as prevalent, even though many downstream tasks may benefit from the emerging properties of reinforcement learning, particularly the enhanced reason capabilities. We study the effects of rule-based reinforcement learning with the task of Document Image Classification which is one of the most commonly studied downstream tasks in document analysis. We find that reinforcement learning tends to have better generalisation capabilities to out-of-distritbution data, which we examine in three different scenarios, namely out-of-distribution images, unseen classes and different modalities. Our code is available at https://github.com/jungomi/vision-finetune.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 23 of its 44 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

23 of 44 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model10 Apr
  2. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization13 Mar
  3. 2025R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model7 Mar
  4. 2025Visual-RFT: Visual Reinforcement Fine-Tuning3 Mar

Other references · 19

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2025Qwen3 Technical Reportcited by 8,820
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  8. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  9. 2025Gemma 3 Technical Reportcited by 1,824
  10. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  11. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
  12. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 329
7 more
  1. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMscited by 289
  2. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learningcited by 173
  3. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Modelscited by 144
  4. 2025Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learningcited by 69
  5. 2025Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generationcited by 58
  6. 2025A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challengescited by 47
  7. 2025Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzlescited by 36

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification
  2. 2025ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents
  3. 2025DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding
  4. 2025Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
  5. 2026Rewards as Labels: Revisiting RLVR from a Classification Perspective
  6. 2023Reinforcement Learning for Generative AI: A Survey
  7. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
  8. 2026RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation