构建可自进化临床记忆图，提升医疗决策准确性
GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning
- 用双层图结构组织临床经验，显式建模决策与关联关系
- 在两个基准上分别达70.90%和69.24%准确率，优于所有基线
- 适合需要可解释、可复用医疗决策的AI系统开发者
临床决策智能体可通过复用过往决策经验获益。然而，许多记忆增强方法将经验存储为独立记录，缺乏明确的关联结构，易导致检索噪声、复用不可靠，甚至比直接使用大模型推理效果更差。我们提出GSEM（基于图的自演化记忆），将临床经验组织为双层记忆图，同时捕捉单个经验内的决策结构及跨经验的依赖关系，并支持基于适用性的检索与在线反馈驱动的节点质量与边权重校准。在MedR-Bench和MedAgentsBench两个基准上，采用DeepSeek-V3.2和Qwen3.5-35B两种LLM后端，GSEM均达到最高平均准确率，分别为70.90%和69.24%。代码已开源：https://github.com/xhan1022/gsem。
原文摘要 · Abstract (English)
Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical memory framework that organizes clinical experiences into a dual-layer memory graph, capturing both the decision structure within each experience and the relational dependencies across experiences, and supporting applicability-aware retrieval and online feedback-driven calibration of node quality and edge weights. Across MedR-Bench and MedAgentsBench with two LLM backbones, GSEM achieves the highest average accuracy among all baselines, reaching 70.90\% and 69.24\% with DeepSeek-V3.2 and Qwen3.5-35B, respectively. Code is available at https://github.com/xhan1022/gsem.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。