ACL Findings2026
MedDCR: Learning to Design Agentic Workflows for Medical Coding
Jiyang Zheng, Islam Nassar, Thanh Vu, Xu Zhong, Yang Lin, Tongliang Liu, Long Duong, Yuan-Fang Li
摘要
Medical coding converts free-text clinical notes into standardized diagnostic and procedural codes, which are essential for billing, hospital operations, and medical research. Unlike ordinary text classification, it requires multistep reasoning: extracting diagnostic concepts, applying guideline constraints, mapping to hierarchical codebooks, and ensuring crossdocument consistency. Recent advances leverage agentic LLMs, but most rely on rigid, manually crafted workflows that fail to capture the nuance and variability of real-world documentation, leaving open the question of how to systematically learn effective workflows. We present MedDCR, a closed-loop framework that treats workflow design as a learning problem. A Designer proposes workflows, a Coder executes them, and a Reflector evaluates predictions and provides constructive feedback, while a memory archive preserves prior designs for reuse and iterative refinement. On benchmark datasets, MedDCR outperforms state-of-the-art baselines and produces interpretable, adaptable workflows that better reflect real coding practice, improving both the reliability and trustworthiness of automated systems.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 1 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- Reflexion: language agents with verbal reinforcement learning 引用了 Toolformer: Language Models Can Teach Themselves to Use Tools
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs 引用了 Reflexion: language agents with verbal reinforcement learning
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs 引用了 Toolformer: Language Models Can Teach Themselves to Use Tools
引用它的顶会 Paper1
它引用的 Paper25
- Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu 等NeurIPS 2023 · 5,989 次引用
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan 等NeurIPS 2023 · 5,828 次引用
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin 等NeurIPS 2023 · 1,975 次引用
- Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum 等ICML 2024 · 1,562 次引用
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsYujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu 等ICLR 2024 · 1,469 次引用
相关 Paper
- Code Like Humans: A Multi-Agent Solution for Medical CodingAndreas Geert Motzfeldt, Joakim Edin, Casper L. Christensen, Christian Hardmeier 等EMNLP Findings 2025 · 5 次引用
- Learning to Be a Doctor: Searching for Effective Medical Agent ArchitecturesYangyang Zhuang, Wenjia Jiang, Jiayu Zhang, Ze Yang 等ACM MM 2025 · 1 次引用
- CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in HealthcareAkash Ghosh, Tajamul Ashraf, Rishu Kumar Singh, Numan Saeed, Sriparna Saha, Xiuying Chen, Salman KhanCVPR Findings 2026
- EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health RecordsWenqi Shi, Ran Xu, Yuchen Zhuang, Yue Yu 等EMNLP 2024 · 33 次引用
- Critic–Adviser–Reviser Cyclic Refinement: Towards High-Quality EMR Corpus Generation with LLMsChen Ning, Xien Liu, Chenwei Yan, Xiao Zhang 等ICLR 2026
