# Exploring LLM Multi-Agents for ICD Coding

arXiv: https://arxiv.org/abs/2406.15363 · HTML: https://mlsanity.com/paper/2406.15363/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 56 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Explainable Prediction of Medical Codes from Clinical Text](https://mlsanity.com/paper/1802.05695/) (2018)
- [A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics](https://mlsanity.com/paper/2310.05694/) (2023)
- [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024)
- [ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network](https://mlsanity.com/paper/1912.00862/) (2019)
- [Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding](https://mlsanity.com/paper/2203.01515/) (2022)
- [Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding](https://mlsanity.com/paper/2210.03304/) (2022)
- [Towards Automated ICD Coding Using Deep Learning](https://mlsanity.com/paper/1711.04075/) (2017)
- [Automated Clinical Coding: What, Why, and Where We Are?](https://mlsanity.com/paper/2203.11092/) (2022)
- [Dilated Convolutional Attention Network for Medical Code Assignment from Clinical Text](https://mlsanity.com/paper/2009.14578/) (2020)
- [Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs](https://mlsanity.com/paper/2010.07459/) (2020)
- [MDACE: MIMIC Documents Annotated with Code Evidence](https://mlsanity.com/paper/2307.03859/) (2023)
- [A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries](https://mlsanity.com/paper/2107.10652/) (2021)
- [Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions](https://mlsanity.com/paper/2011.06874/) (2020)

## Built on by (most cited first, 14 of 14)

- [Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews](https://mlsanity.com/paper/2502.05439/) (2025)
- [Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding](https://mlsanity.com/paper/2505.21908/) (2025)
- [Can Reasoning LLMs Enhance Clinical Document Classification?](https://mlsanity.com/paper/2504.08040/) (2025)
- [MedDCR: Learning to Design Agentic Workflows for Medical Coding](https://mlsanity.com/paper/2511.13361/) (2025)
- [Benchmarking Chinese Medical LLMs: A Medbench-based Analysis of Performance Gaps and Hierarchical Optimization Strategies](https://mlsanity.com/paper/2503.07306/) (2025)
- [MedGellan: LLM-Generated Medical Guidance to Support Physicians](https://mlsanity.com/paper/2507.04431/) (2025)
- [ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts](https://mlsanity.com/paper/2511.11883/) (2025)
- [AnimAgents: Coordinating Multi-Stage Animation Pre-Production with Human-Multi-Agent Collaboration](https://mlsanity.com/paper/2511.17906/) (2025)
- [Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents](https://mlsanity.com/paper/2602.04813/) (2026)
- [Symphony for Medical Coding: A Next-Generation Agentic System for Scalable and Explainable Medical Coding](https://mlsanity.com/paper/2603.29709/) (2026)
- [KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs](https://mlsanity.com/paper/2608.20887/) (2026)
- [Using LLMs for Multilingual Clinical Entity Linking to ICD-10](https://mlsanity.com/paper/2509.04868/) (2025)
- [Enhancing LLM Medical Coding with Structured External Knowledge](https://mlsanity.com/paper/2605.27377/) (2026)
- [LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents](https://mlsanity.com/paper/2609.19721/) (2026)

## Abstract (arXiv)

To address the limitations of Large Language Models (LLMs) in the International Classification of Diseases (ICD) coding task, where they often produce inaccurate and incomplete prediction results due to the high-dimensional and skewed distribution of the ICD codes, and often lack interpretability and reliability as well. We introduce an innovative multi-agent approach for ICD coding which mimics the ICD coding assignment procedure in real-world settings, comprising five distinct agents: the patient, physician, coder, reviewer, and adjuster. Each agent utilizes an LLM-based model tailored to their specific role within the coding process. We also integrate the system with Electronic Health Record (HER)'s SOAP (subjective, objective, assessment and plan) structure to boost the performances. We compare our method with a system of agents designed solely by LLMs and other strong baselines and evaluate it using the Medical Information Mart for Intensive Care III (MIMIC-III) dataset. Our multi-agent coding framework significantly outperforms Zero-shot Chain of Thought (CoT) prompting and self-consistency with CoT (CoT-SC) in coding common and rare ICD codes. An ablation study validates the effectiveness of the designated agent roles. it also outperforms the LLM-designed agent system. Moreover, our method achieves comparable results to state-of-the-art ICD coding methods that require extensive pre-training or fine-tuning, and outperforms them in rare code accuracy, and explainability. Additionally, we demonstrate the method's practical applicability by presenting its performance in scenarios not limited by the common or rare ICD code constraints.The proposed multi-agent method for ICD coding effectively mimics the real-world coding process and improves performance on both common and rare codes.