# Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding

arXiv: https://arxiv.org/abs/2505.21908 · HTML: https://mlsanity.com/paper/2505.21908/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 32 of its 51 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Learning to Reason under Off-Policy Guidance](https://mlsanity.com/paper/2504.14945/) (2025)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning](https://mlsanity.com/paper/2504.02546/) (2025)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [Rule Based Rewards for Language Model Safety](https://mlsanity.com/paper/2411.01111/) (2024)
- [Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning](https://mlsanity.com/paper/2504.03380/) (2025)
- [CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models](https://mlsanity.com/paper/2503.22342/) (2025)
- [SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM](https://mlsanity.com/paper/2504.14286/) (2025)
- [Automated Clinical Coding: What, Why, and Where We Are?](https://mlsanity.com/paper/2203.11092/) (2022)
- [DRG-LLaMA : Tuning LLaMA Model to Predict Diagnosis-related Group for Hospitalized Patients](https://mlsanity.com/paper/2309.12625/) (2023)
- [Exploring LLM Multi-Agents for ICD Coding](https://mlsanity.com/paper/2406.15363/) (2024)
- [How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study](https://mlsanity.com/paper/2504.00829/) (2025)
- [Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding](https://mlsanity.com/paper/2405.19567/) (2024)

## Built on by (most cited first, 7 of 7)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [RL Fine-Tuning Heals OOD Forgetting in SFT](https://mlsanity.com/paper/2509.12235/) (2025)
- [RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs](https://mlsanity.com/paper/2508.16546/) (2025)
- [Libra: Efficient Resource Management for Agentic RL Post-Training](https://mlsanity.com/paper/2606.03077/) (2026)
- [Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning](https://mlsanity.com/paper/2604.15705/) (2026)
- [Reinforced Curriculum Pre-Alignment for Domain-Adaptive VLMs](https://mlsanity.com/paper/2602.10740/) (2026)
- [The NordDRG AI Benchmark for Large Language Models](https://mlsanity.com/paper/2506.13790/) (2025)

## Abstract (arXiv)

Diagnosis-Related Group (DRG) codes are essential for hospital reimbursement and operations but require labor-intensive assignment. Large Language Models (LLMs) struggle with DRG coding due to the out-of-distribution (OOD) nature of the task: pretraining corpora rarely contain private clinical or billing data. We introduce DRG-Sapphire, which uses large-scale reinforcement learning (RL) for automated DRG coding from clinical notes. Built on Qwen2.5-7B and trained with Group Relative Policy Optimization (GRPO) using rule-based rewards, DRG-Sapphire introduces a series of RL enhancements to address domain-specific challenges not seen in previous mathematical tasks. Our model achieves state-of-the-art accuracy on the MIMIC-IV benchmark and generates physician-validated reasoning for DRG assignments, significantly enhancing explainability. Our study further sheds light on broader challenges of applying RL to knowledge-intensive, OOD tasks. We observe that RL performance scales approximately linearly with the logarithm of the number of supervised fine-tuning (SFT) examples, suggesting that RL effectiveness is fundamentally constrained by the domain knowledge encoded in the base model. For OOD tasks like DRG coding, strong RL performance requires sufficient knowledge infusion prior to RL. Consequently, scaling SFT may be more effective and computationally efficient than scaling RL alone for such tasks.