Elamur Research⌕
☰
home / papers / 2026 / MedDCR: Learning to Design Agentic Workflows for Medical Coding

MedDCR: Learning to Design Agentic Workflows for Medical Coding

Paper · 2026 · Jiyang Zheng, Islam Nassar, Thanh Vu et al.

Summary

Assigning ICD codes to clinical notes involves several reasoning stages: spotting diagnoses, consulting code indexes, enforcing guideline rules and checking consistency. Earlier LLM-agent systems for this task depend on pipelines that experts build by hand, and these can miss better ways of combining tools and strategies. MedDCR reframes pipeline construction as something to be learned. Three LLM agents work in a loop:

  • a Designer drafts a workflow from a library of general reasoning strategies and coding-specific tools,
  • a Coder turns it into an executable program and repairs it if it fails,
  • a Reflector scores the resulting predictions and writes textual critique.

A memory archive keeps every earlier design so that both strong and recent workflows can guide the next proposal. Expert-made pipelines can also be added as seeds. On the MDACE and ACI-BENCH benchmarks, the learned workflows beat both PLM-based classifiers and hand-built agentic baselines, and the search adds little cost. The work suggests that automatically discovered, inspectable workflows could make automated coding more accurate and more trustworthy than static designs.

Key points

  • Compared with the second-best baseline, MedDCR raises F1 by 6.2% on MDACE and 7.4% on ACI-BENCH. With GPT-5, it reaches Micro-F1 0.51 on MDACE and F1 0.52 on ACI-BENCH.
  • Search overhead is small. The search tokens consumed in a single loop stay below 20k for MDACE and 15k for ACI-BENCH. Total cost is $17.09 and $5.72 per 100 inference samples respectively, and most of it comes from executing workflows rather than searching for them.
  • In plug-and-play tests seeded with a CoT-SC workflow, optimisation alone moves F1 from 0.41 to 0.42. Adding all auxiliary seeds lifts it to 0.47, which is better than searching from scratch.
  • The ablations on MDACE single out memory selection as most important. Removing the top-k archive entries lowers F1 by 0.09, and removing the recent-n entries lowers it by 0.13. Dropping the Reflector's feedback or the meta-prompt exemplars also hurts performance.
  • The authors list several limitations: the GPT models are not fine-tuned for medicine, the Reflector's feedback is heuristic, and evaluation covers only ICD-10, with no multi-taxonomy or multilingual settings.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓The University of SydneySydney · Australia45 works · 68,350 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksBiochemistry, Genetics and Molecular Biology · 234 worksMolecular Biology · 231 worksHealth Professions · 69 worksHealth Information Management · 50 works

Cite

Cite as Jiyang Zheng, Islam Nassar, Thanh Vu, Xu Zhong, Yang Lin, Tongliang Liu, Long Duong and Yuan-Fang Li. 2026. MedDCR: Learning to Design Agentic Workflows for Medical Coding. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.627

@inproceedings{zheng2026meddcr,
  title = {{MedDCR: Learning to Design Agentic Workflows for Medical Coding}},
  author = {Jiyang Zheng, Islam Nassar, Thanh Vu, Xu Zhong, Yang Lin, Tongliang Liu, Long Duong and Yuan-Fang Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.627},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.627}
}

References

66 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Vera Alonso, João Vasco Santos, Marta Pinto, Joana Ferreira, Isabel Lema, Fernando Lopes, and Alberto Freitas. 2020. Problems and barriers during the process of clinical coding: a focus group study of coders’ perceptions. Journal of medical systems, 44(3):62. find
  2. MSA Ann Barta. 2009. Icd-10-cm official coding guidelines. Journal of AHIMA. find
  3. Krishanu Das Baksi, Elijah Soba, John J Higgins, Ravi Saini, Jaden Wood, Jane Cook, Jack I Scott, Nirmala Pudota, Tim Weninger, Edward Bowen, and 1 others. 2025. Medcoder: A generative ai assistant for medical coding. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of th… find
  4. Joseph Spartacus Boyle, Antanas Kascenas, Pat Lok, Maria Liakata, and Alison Q O’Neil. 2023. Automated clinical coding using off-the-shelf large language models. In Deep Generative Models for Health Workshop, Advances in neural information processing systems. find
  5. Sharon Campbell and Katrina Giadresco. 2020. Computer-assisted clinical coding: A narrative review of the literature on its benefits, limitations, implementation and impact on clinical coding professionals. Health Information Management Journal, 49(1):5–18. find
  6. Pengfei Cao, Chenwei Yan, Xiangling Fu, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu, and Weifeng Chong. 2020. Clinical-coder: Assigning interpretable icd-10 codes to chinese clinical notes. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrat… find
  7. Banghao Chen, Zhaofeng Zhang, Nicolas Langrené, and Shengxin Zhu. 2023. Unleashing the potential of prompt engineering in large language models: a comprehensive review. arXiv preprint arXiv:2310.14735.
  8. Hua Cheng, Rana Jafari, April Russell, Russell Klopfer, Edmond Lu, Benjamin Striner, and Matthew Gormley. 2023. MDACE: MIMIC documents annotated with code evidence. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7534– 7550. find
  9. Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2024. Chain-of-verification reduces hallucination in large language models. In Findings of the Association for Computational Linguistics ACL 2024, pages 3563–3578.
  10. Hang Dong, Matúš Falis, William Whiteley, Beatrice Alex, Joshua Matterson, Shaoxiong Ji, Jiaoyan Chen, and Honghan Wu. 2022. Automated clinical coding: what, why, and where we are? NPJ digital medicine, 5(1):159. find
  11. Hang Dong, Víctor Suárez-Paniagua, William Whiteley, and Honghan Wu. 2021. Explainable automated coding of clinical notes using hierarchical label-wise attention networks and label embedding initialisation. Journal of biomedical informatics, 116:103728. find
  12. James C Douglas, Yidong Gan, Ben Hachey, and Jonathan K Kummerfeld. 2025. Less is more: Explainable and efficient icd code prediction with clinical entities. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 30835–30847. find
  13. Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. Improving factuality and reasoning in language models through multiagent debate. In Forty-first International Conference on Machine Learning.
  14. Joakim Edin, Maria Maistro, Lars Maaløe, Lasse Borgholt, Jakob Havtorn, and Tuukka Ruotsalo. 2024. An unsupervised approach to achieve supervised-level explainability in healthcare records. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4869–4890. find
  15. Matúš Falis, Aryo Pradipta Gema, Hang Dong, Luke Daines, Siddharth Basetti, Michael Holder, Rose S Penfold, Alexandra Birch, and Beatrice Alex. 2024. Can gpt-3.5 generate and code discharge summaries? Journal of the American Medical Informatics Association, 31(10):2284–2293. find
  16. Harshit Joshi, José Cambronero Sanchez, Sumit Gulwani, Vu Le, Gust Verbruggen, and Ivan Radiček. 2023. Repair is nearly generation: Multilingual program repair with llms. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 5131– 5140. find
  17. Richárd Farkas and György Szarvas. 2008. Automatic construction of rule-based icd-9-cm coding systems. BMC bioinformatics, 9(Suppl 3):S10. find
  18. Ramakanth Kavuluru, Anthony Rios, and Yuan Lu. 2015. An empirical evaluation of supervised learning approaches in assigning diagnosis codes to electronic medical records. Artificial intelligence in medicine, 65(2):155–166. find
  19. Chrisantha Fernando, Dylan Sunil Banarse, Henryk Michalewski, Simon Osindero, and Tim Rocktäschel. 2024. Promptbreeder: Self-referential self-improvement via prompt evolution. In Forty-first International Conference on Machine Learning.
  20. Yidong Gan, Maciej Rybinski, Ben Hachey, and Jonathan K. Kummerfeld. 2025. Aligning AI research with the needs of clinical coding workflows: Eight recommendations based on US data analysis and critical review. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics… find
  21. Zelalem Gero, Chandan Singh, Hao Cheng, Tristan Naumann, Michel Galley, Jianfeng Gao, and Hoifung Poon. 2023. Self-verification improves few-shot clinical information extraction. In ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH).
  22. Akshay Goel. 2025. LangExtract. find
  23. Shengran Hu, Cong Lu, and Jeff Clune. 2025. Automated design of agentic systems. In The Thirteenth International Conference on Learning Representations. find
  24. Chao-Wei Huang, Shang-Chi Tsai, and Yun-Nung Chen. 2022. Plm-icd: Automatic icd coding with pretrained language models. find
  25. ClinicalNLP 2022, page 10. find
  26. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  27. Shaoxiong Ji, Xiaobo Li, Wei Sun, Hang Dong, Ara Taalas, Yijia Zhang, Honghan Wu, Esa Pitkänen, and Pekka Marttinen. 2024. A unified review of deep learning for automated medical coding. ACM Computing Surveys, 56(12):1–41. find
  28. Alistair Johnson, Lucas Bulgarelli, Tom Pollard, Steven Horng, Leo Anthony Celi, and Roger Mark. 2020. Mimic-iv. PhysioNet. Available online at: https://physionet. org/content/mimiciv/1.0/(accessed August 23, 2021), pages 49–55. find
  29. Alistair EW Johnson, Tom J Pollard, Lu Shen, Li-wei H Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. Mimic-iii, a freely accessible critical care database. Scientific data, 3(1):1–9.
  30. Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Saiful Haq, Ashutosh Sharma, Thomas T Joshi, Hanna Moazam, Heather Miller, and 1 others. 2024. Dspy: Compiling declarative language model calls into state-of-the-art pipelines. In The Twelfth International Conference o… find
  31. Keith Kwan. 2024. Large language models are good medical coders, if provided with tools. arXiv preprint arXiv:2407.12849. — [arXiv:2407.12849](https://arxiv.org/abs/2407.12849) find
  32. Fei Li and Hong Yu. 2020. Icd coding from clinical text using multi-filter residual convolutional neural network. In proceedings of the AAAI conference on artificial intelligence, pages 8180–8187. find
  33. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. Camel: Communicative agents for" mind" exploration of large language model society. Advances in Neural Information Processing Systems, 36:51991–52008.
  34. Junyou Li, Qin Zhang, Yangbin Yu, QIANG FU, and Deheng Ye. 2024a. More agents is all you need. Transactions on Machine Learning Research. find
  35. Rumeng Li, Xun Wang, and Hong Yu. 2024b. Exploring llm multi-agents for icd coding. arXiv preprint arXiv:2406.15363. — [arXiv:2406.15363](https://arxiv.org/abs/2406.15363) find
  36. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024. Encouraging divergent thinking in large language models through multi-agent debate. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17…
  37. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, and 1 others. 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36:46534–46594. find
  38. Andreas Motzfeldt, Joakim Edin, Casper L Christensen, Christian Hardmeier, Lars Maaløe, and Anna Rogers. 2025. Code like humans: A multi-agent solution for medical coding. arXiv preprint arXiv:2509.05378. find
  39. James Mullenbach, Sarah Wiegreffe, Jon Duke, Jimeng Sun, and Jacob Eisenstein. 2018. Explainable prediction of medical codes from clinical text. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1…
  40. Akram Mustafa, Usman Naseem, and Mostafa Rahimi Azghadi. 2025. Evaluating hierarchical clinical document classification using reasoning-based llms. arXiv preprint arXiv:2507.03001. — [arXiv:2507.03001](https://arxiv.org/abs/2507.03001) find
  41. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, and 1 others. 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332.
  42. Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao, and Armando Solar-Lezama. 2024. Is self-repair a silver bullet for code generation? In The Twelfth International Conference on Learning Representations. find
  43. Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, and Michael Zeng. 2023. Automatic prompt optimization with ”gradient descent” and beam search. In The 2023 Conference on Empirical Methods in Natural Language Processing.
  44. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, dahai li, Zhiyuan Liu, and Maosong Sun. 2024. ToolLLM: Facilitating large language models to master 16000+ real…
  45. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36:68539–68551.
  46. Murray Shanahan, Kyle McDonell, and Laria Reynolds. 2023. Role play with large language models. Nature, 623(7987):493–498.
  47. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36:8634–8652.
  48. Thanh Vu, Dat Quoc Nguyen, and Anthony Nguyen. 2021. A label attention model for icd coding from clinical text. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 3335–3341. find
  49. Wenxiao Wang, Priyatham Kattakinda, and Soheil Feizi. 2025. Maestro: Joint graph & config optimization for reliable ai agents. arXiv preprint arXiv:2509.04642. — [arXiv:2509.04642](https://arxiv.org/abs/2509.04642) find
  50. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023a. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations.
  51. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023b. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations.
  52. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824– 24837.
  53. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, and 1 others. 2024. Autogen: Enabling next-gen llm applications via multi-agent conversations. In First Conference on Language Modeling. find
  54. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023a. Large language models as optimizers. In The Twelfth International Conference on Learning Representations.
  55. Zhichao Yang, Sanjit Singh Batra, Joel Stremmel, and Eran Halperin. 2023b. Surpassing gpt-4 medical coding with a two-stage approach. arXiv preprint arXiv:2311.13735. — [arXiv:2311.13735](https://arxiv.org/abs/2311.13735) find
  56. Zhichao Yang, Sunjae Kwon, Zonghai Yao, and Hong Yu. 2023c. Multi-label few-shot icd coding as autoregressive generation with prompt. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 5366–5374. find
  57. Wen-wai Yim, Yujuan Fu, Asma Ben Abacha, Neal Snider, Thomas Lin, and Meliha Yetisgen. 2023. Aci-bench: a novel ambient clinical intelligence dataset for benchmarking automatic visit note generation. Nature Scientific Data. find
  58. Zheng Yuan, Chuanqi Tan, and Songfang Huang. 2022. Code synonyms do matter: Multiple synonyms matching network for automatic icd coding. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 808–814. find
  59. Guibin Zhang, Luyang Niu, Junfeng Fang, Kun Wang, LEI BAI, and Xiang Wang. 2025a. Multi-agent architecture search via agentic supernet. In Forty-second International Conference on Machine Learning. find
  60. Jialu Zhang, José Pablo Cambronero, Sumit Gulwani, Vu Le, Ruzica Piskac, Gustavo Soares, and Gust Verbruggen. 2024. Pydex: Repairing bugs in introductory python assignments using llms. Proceedings of the ACM on Programming Languages, 8(OOPSLA1):1100–1124. find
  61. “The patient was admitted for acute myocardial infarction and underwent coronary artery bypass graft (CABG). The postoperative course was uncomplicated.” Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xiong-Hui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng… find
  62. A correct ICD-10-CM coding outcome for this note includes: Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2023. Automatic chain of thought prompting in large language models. In The Eleventh International Conference on Learning Representations.
  63. I21.3 — ST elevation (STEMI) of unspecified site. and for ICD-10-PCS (procedure codes): • 021009W — Bypass coronary artery, one site, autologous vein, open approach. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, and… — Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
  64. Challenges. Accurate code assignment requires multiple reasoning steps: Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. 2024. Memorybank: Enhancing large language models with long-term memory. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 19724–19731. 2. Cons… find
  65. Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, and Sercan Ö Arık. 2025. Multi-agent design: Optimizing agents with better prompts and topologies. arXiv preprint arXiv:2502.02533. — [arXiv:2502.02533](https://arxiv.org/abs/2502.02533) find
  66. Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, and 1 others. 2023. Ghost in the minecraft: Generally capable agents for open-world environments via large language models with text-based knowledge and memory. arXiv preprint arXiv:23… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zheng-2026-meddcr-learning-design-agentic-workflows/