ICDAGENT: Empowering Agentic Large Language Models for Explainable Medical Coding

The explainable medical coding task aims to automatically assign International Classification of Diseases (ICD) codes to clinical notes while providing explicit justifications for each assignment. Recent approaches employ large language models (LLMs) to generate such explanations. However, their performance remains limited due to a lack of understanding of the clinical meanings of ICD codes. Additionally, the vast ICD code space further complicates the task of accurate prediction. To address these challenges, we propose the ICDAGENT framework, which consists of two collaborative LLM agents: a coding agent and a critical agent. The coding agent extracts ICD codes and generates preliminary rationales, while the critical agent performs fine-grained chain-of-thought reasoning to verify and refine them. Furthermore, the critical agent is trained with a rationaleaware reward, combined with reinforcement learning, enabling it to distinguish between correct and incorrect reasoning and ensure explanation accuracy. Experiments across multiple ICD coding standards and datasets demonstrate that ICDAGENT achieves effective ICD coding with accurate and trustworthy explanations. 1 * Corresponding author. 1 The source code will be available at https://github. com/ericyinyzy/ICDAGENT.git . 15 20 25 30 35 40 45 40 43 46 49 52 55 58 Precision (%) Recall (%) Claude-4-Sonnet Claude-3.7-Sonnet Gemini-2.5-Pro Gemini-2.5-Flash GPT-5-Chat (Azure) GPT-4o (Azure) ICDAGENT (Ours) LoRA Fine-tuning HuatuoGPT-o1-8B Clinical Note 𝐓𝐓