MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction· MediSkill-Evo：证据支持的临床交互自进化
Interactive clinical agents must gather decisive evidence and convert it into grounded actions under partial observability. A correct final diagnosis alone does not show that an agent respected evidence and care-process constraints. We introduce MediSkill-Evo, a clinical agent that evolves governed process knowledge without backbone fine-tuning. It separates experience into four typed banks for clinical skills, process rules, symbolic schemas, and measurement procedures. Provenance, support, replay, and controller-defined safety checks govern publication to a frozen test-time snapshot. A Process-Constrained Preference Harness binds evidence to its source, rejects controller-invalid candidates, and ranks actions with a safety-prioritized Clinical Process Critic. We evaluate complete agent s
MediSkill-Evo 通过自进化机制在临床交互中确保证据支持和过程约束。
- 核心方法
- MediSkill-Evo 将经验分为四类存储库，并通过来源绑定、支持、重放和安全性检查来治理知识的发布。使用 Process-Constrained Preference Harness 结合证据源，排除无效行为，安全优先地评估行动。
- 适合谁读
- 研究者、工程师、医疗产品开发人员
- 要解决的问题
- 现有的临床交互代理在部分可观察条件下难以确保行为基于证据并遵守医疗过程约束。
- 关键实验
- 在完整的代理评估中展示其性能，但具体实验细节未提供。
- 主要贡献
- 提出了一种新型的临床交互代理自进化框架，能够有效结合证据和过程约束，提升诊断和治疗的可靠性。
- 意义与局限
- MediSkill-Evo 对提高医疗领域的自动化代理的可靠性和安全性有重要影响，但也存在对特定医疗流程的高度依赖，可能限制其广义应用。