MedTextWeaver: Procedural Knowledge Evolution in Agentic Medical Text Editing

arXiv:2602.00740v2 Announce Type: replace Abstract: Medical text editing is essential for improving communication among diverse stakeholders in clinical settings. However, adapting LLM agents to this task remains challenging because expert supervision is often sparse, fragmented, and distributed across interacting quality dimensions. We identify that direct accumulation or retrieval of individual feedback is insufficient for effective adaptation, as fragmented evaluations do not directly translate into a coherent understanding of medical text quality. Based on this observation, we propose MedTextWeaver, a training-free framework that transforms fragmented evaluative evidence into global quality principles and actionable procedural knowledge for medical text editing. Across three clinical text datasets and a real-world validation experiment, MedTextWeaver consistently improves performance over strong LLM baselines and existing memory-based adaptation approaches. Further analysis demonstrates that the learned knowledge enables more effective adaptation under limited supervision while providing an explicit and interpretable interface between expert evaluations and LLM editing behavior.

Related

• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
• Memp: Exploring Agent Procedural Memory
• Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives

Source: arXiv cs.CL | 2026-08-04