资源 · 2026
Generating interpretable clinical reasoning chains in TCM via group relative policy optimization and multi-dimensional rewards
Biomedical Signal Processing and Control
「Generating interpretable clinical reasoning chains in TCM via group relative policy optimization and multi-dimensional rewards」是 中医大模型开源资源目录（Awesome-TCM-LLM）收录的资源，记录于 2026。该条目属于中医大模型（TCM LLM）领域，与 GitHub 列表同源维护。
以组相对策略优化和多维奖励，生成可解释的中医临床推理链。