Tag
DeepTCM1.0 is a multi-expert AI agent framework built on the DeepSeek V3.2 large language model to decipher the mechanisms of Chinese herbal formulae, validated with Guizhi Decoction and evaluated through a comprehensive scoring system.
This paper introduces MMIR-TCM, a novel framework that integrates multimodal large language models with memory-augmented segmentation and retrieval-augmented generation to support Traditional Chinese Medicine clinical decision making, along with a new dataset MedTCM and evaluation metric TDEU.
Exploring the possibilities and prospects of combining AI with Traditional Chinese Medicine.
This paper proposes a knowledge-enhanced visual diagnostic system for traditional Chinese medicine that uses a Neo4j knowledge graph, a four-stage symptom matching pipeline, and an information gain-driven proactive questioning strategy to improve transparency and interpretability. Results demonstrate significant improvements in diagnostic trust and reduced cognitive load.
Someone developed a Traditional Chinese Medicine Agent Skill for Claude Code, structuring all 12 courses of Ni Haixia (including lecture notes, prescriptions, acupoints, and 2,986 course screenshots). It supports natural language retrieval of classical prescriptions and acupoint plans, and can generate study plans and comparison tables. This project demonstrates the penetration of AI agents into traditional knowledge domains.