Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory

• URL: http://arxiv.org/abs/2606.09365v3
• Date: Mon, 15 Jun 2026 15:01:33 GMT
• Title: Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
• Abstract summary: SkeMex is a post-deployment framework that improves medical agents through a skill-based memory without updating model weights.<n>It distills informative interaction trajectories into structured skills that encode reusable procedural knowledge.<n>It estimates context-dependent utility from environment feedback and uses it to guide value-aware retrieval and repository governance.
• Score: 43.487137083499704
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Analytic Concept-Centric Memory for Agentic Embodied Manipulation [67.98329043920803]
  Long-horizon embodied manipulation requires agents to remember persistent objects, track changing scene states, and reuse prior interaction knowledge.<n>Existing agent memories are often stored as unstructured histories or embedding-based records.<n>We propose an analytic concept-centric memory framework for agentic embodied manipulation.
  arXiv  Detail & Related papers  (2026-06-29T04:33:04Z)
• AdMem: Advanced Memory for Task-solving Agents [13.611633561917513]
  Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge.<n>We introduce a unified and automatic memory framework that integrates semantic, episodic, and procedural memory in a bi-level design combining short-term and long-term stores.
  arXiv  Detail & Related papers  (2026-06-05T00:11:57Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• Contextual Agentic Memory is a Memo, Not True Memory [3.939241105154204]
  We argue that treating lookup as memory is a category error with provable consequences for agent capability, long-term learning, and security.<n>We show that biological intelligence solved this problem by pairing fast hippocampal storage with slow neocortical weight consolidation.
  arXiv  Detail & Related papers  (2026-04-30T10:54:56Z)
• Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers [0.42061757959666934]
  Large language model (LLM) agents increasingly operate in settings where a single context window is too small to capture what has happened.<n>Memory is what turns a stateless text generator into a genuinely adaptive agent.<n>This survey offers a structured account of how memory is designed, implemented, and evaluated in modern LLM-based agents.
  arXiv  Detail & Related papers  (2026-03-08T15:08:01Z)
• Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning [44.94110361062394]
  Decision-making in the real world depends on memory that is both stable and adaptive.<n>Existing Reinforcement Learning benchmarks and memory-augmented agents focus primarily on retention.<n>We introduce a benchmark that explicitly tests continual memory updating under partial observability.
  arXiv  Detail & Related papers  (2026-01-21T15:27:23Z)
• Memory in the Age of AI Agents [217.9368190980982]
  This work aims to provide an up-to-date landscape of current agent memory research.<n>We identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory.<n>To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks.
  arXiv  Detail & Related papers  (2025-12-15T17:22:34Z)
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution [52.76038908826961]
  We propose $textbfReMe$ ($textitRemember Me, Refine Me$) to bridge the gap between static storage and dynamic reasoning.<n>ReMe innovates across the memory lifecycle via three mechanisms: $textitmulti-faceted distillation$, which extracts fine-grained experiences.<n>Experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system.
  arXiv  Detail & Related papers  (2025-12-11T14:40:01Z)
• MemVerse: Multimodal Memory for Lifelong Learning Agents [35.218549149012844]
  We introduce MemVerse, a model-agnostic, plug-and-play memory framework.<n>MemVerse bridges fast parametric recall with hierarchical retrieval-based memory.<n>It enables scalable and adaptive multimodal intelligence.
  arXiv  Detail & Related papers  (2025-12-03T10:06:14Z)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory [57.517214479414726]
  ReasoningBank is a memory framework that distills generalizable reasoning strategies from an agent's self-judged successful and failed experiences.<n>At test time, an agent retrieves relevant memories from ReasoningBank to inform its interaction and then integrates new learnings back, enabling it to become more capable over time.<n>We introduce memory-aware test-time scaling (MaTTS), which accelerates and diversifies this learning process by scaling up the agent's interaction experience.
  arXiv  Detail & Related papers  (2025-09-29T17:51:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.