# Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation

arXiv: https://arxiv.org/abs/2508.12957 · HTML: https://mlsanity.com/paper/2508.12957/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 27 of 27)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [VisualPRM: An Effective Process Reward Model for Multimodal Reasoning](https://mlsanity.com/paper/2503.10291/) (2025)
- [MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs](https://mlsanity.com/paper/2504.00993/) (2025)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [Reward Collapse in Aligning Large Language Models](https://mlsanity.com/paper/2305.17608/) (2023)
- [Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning](https://mlsanity.com/paper/2505.19213/) (2025)
- [Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme](https://mlsanity.com/paper/2504.02587/) (2025)
- [GEMeX-RMCoT: An Enhanced Med-VQA Dataset for Region-Aware Multimodal Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.17939/) (2025)

## Built on by (most cited first, 4 of 4)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle](https://mlsanity.com/paper/2509.16679/) (2025)
- [Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning](https://mlsanity.com/paper/2606.31825/) (2026)
- [MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models](https://mlsanity.com/paper/2603.19044/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) with rule-based reward functions has recently shown great promise in enhancing the reasoning depth and generalization ability of vision-language models (VLMs), while maintaining computational efficiency. In spite of these advances, its adoption in medical imaging remains limited. Current reinforcement fine-tuning (RFT) efforts in this field mainly focus on closed-ended visual question answering (VQA), restricting their applicability to realistic clinical reasoning. However, open-ended medical VQA better mirrors clinical diagnostic workflows but remains underexplored. Although several studies have attempted to bridge the two formats through semantically guided RL, model-driven semantic rewards often suffer from reward collapse, where responses with distinct semantics yield nearly identical scores. To overcome this limitation, we introduce Adaptive Reinforcement for Medical Reasoning (ARMed), a novel RL framework tailored for open-ended medical VQA. ARMed first injects domain expertise through supervised fine-tuning (SFT) on chain-of-thought annotations, followed by reinforcement optimization using textual correctness and adaptive semantic rewards to refine reasoning consistency and factual accuracy. Extensive experiments on six challenging medical VQA benchmarks demonstrate that ARMed substantially improves both accuracy and generalization. These findings underscore the importance of reward discriminability in medical RL and highlight the potential of adaptive semantic rewards for building robust, clinically reliable multimodal reasoning systems.