SkeMex：通过自进化技能记忆实现可泛化的医疗智能体推理
Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
研究者提出 SkeMex，一个部署后自进化框架，通过技能记忆提升医疗智能体推理能力且不更新模型权重。SkeMex 将交互轨迹蒸馏为结构化技能，组织成覆盖通用、任务特定和动作级经验的多分支仓库，并依据环境反馈估计上下文相关效用，指导价值感知检索与仓库治理。在多种临床任务中，SkeMex 在离线和在线设置下均持续优于代表性记忆型智能体，并可跨模型骨干泛化，支持可迁移的技能记忆。
Authors:Haoran Sun, Wenjie Li, Yujie Zhang, Zekai Lin, Fanrui Zhang, Kaitao Chen, Xingqi He, Yichen Li, Mianxin Liu, Lei Liu, Yankai Jiang
Abstract:Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective agents must reuse prior experience across evolving cases, yet existing memory mechanisms often retain raw historical traces that are redundant, noisy, and difficult to govern. More importantly, they rarely distinguish which memories are truly useful for future reasoning. This limits their ability to accumulate compact and reliable experience for long-horizon clinical reasoning. To close this gap, we propose SkeMex, a post-deployment self-evolution framework that improves medical agents through a skill-based memory without updating model weights. SkeMex distills informative interaction trajectories into structured skills that encode reusable procedural knowledge, and organizes them into a multi-branch repository spanning general, task-specific, and action-level experience. To determine which memories should be reused and retained, SkeMex estimates context-dependent utility from environment feedback and uses it to guide value-aware retrieval and repository governance. A closed-loop ``Read--Write--Assess--Govern" lifecycle further supports continual evolution by writing new skills, updating utilities, promoting useful memories, and removing harmful entries. Experiments across diverse clinical tasks show that SkeMex consistently outperforms representative memory-based agents in both offline and online settings. It also generalizes across model backbones and supports transferable skill memory. All data and code will be released publicly.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.09365 [cs.AI] |
| (or arXiv:2606.09365v4 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.09365 arXiv-issued DOI via DataCite |
Submission history
From: Haoran Sun [view email]
[v1]
Mon, 8 Jun 2026 11:37:01 UTC (19,046 KB)
[v2]
Wed, 10 Jun 2026 14:46:00 UTC (19,046 KB)
[v3]
Mon, 15 Jun 2026 15:01:33 UTC (19,046 KB)
[v4]
Fri, 9 Oct 2026 07:02:59 UTC (19,057 KB)
来源：arXiv cs.CL · arxiv.org