ERSkill：面向技能引导的自适应记忆检索的演化框架
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
- Shenzhen International Center for Industrial and Applied Mathematics（深圳国际工业与应用数学中心）
- Shenzhen Research Institute of Big Data（深圳大数据研究院）
- The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
- Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）
- Shenzhen Loop Area Institute（深圳河套学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ERSkill是一个以检索为核心的自演化技能引导记忆访问框架，通过协同演化技能集与路由器，在多个智能体记忆基准上大幅超越基线，在两款模型上分别实现31.3%、28.1%的指标提升。
AI中文摘要：
尽管大型语言模型（LLM）智能体越来越依赖长期记忆来进行持续交互，但支配该记忆的检索机制很少被视为可演化的组件。这种静态方法限制了其在异构记忆查询上的性能，这类查询往往需要多样化的证据构建策略。为解决这一问题，我们提出ERSkill，这是一个以检索为核心的自演化、技能引导的记忆访问框架。ERSkill将交互历史编译为结构化记忆存储，并将检索行为表示为由基本原语组成的可执行技能。推理时，训练好的路由器会动态将每个查询匹配到最优技能，以构建定制化证据用于答案生成。为实现持续改进，ERSkill在训练过程中协同演化技能集与路由器，它采用经验前缀树（experience trie）高效记录已探索的检索路径，同时运用双前沿机制，安全地将新技能能力的扩展与面向稳定路由器的部署解耦。在多个智能体记忆基准上的实验表明，ERSkill大幅优于强大的非演化和自演化基线，值得注意的是，它在Qwen3-Next-80B-A3B-Instruct上提升了F1、BLEU-1和LLM评判分数的总体平均值31.3%，在GPT-5.4-nano上提升了28.1%。
英文摘要：
While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely treated as evolvable components. This static approach limits performance on heterogeneous memory queries, which often demand diverse evidence construction strategies. To address this, we introduce \textbf{ERSkill}, a retrieval-centric framework for evolving, skill-guided memory access. ERSkill compiles interaction histories into a structured memory store and represents retrieval behaviors as executable skills composed of fundamental primitives. At inference time, a trained router dynamically matches each query to a suitable retrieval skill to construct tailored evidence for answer generation. ERSkill co-evolves the skill set and the router during training. It employs an experience trie to efficiently record explored retrieval paths, alongside a double-frontier mechanism that separates oracle-side capability expansion from router-validated deployment. Experiments across multiple agent memory benchmarks demonstrate that ERSkill substantially outperforms strong non-evolving and evolving baselines. Notably, it improves the overall average across F1, BLEU-1, and LLM-judge scores by 31.3\% with Qwen3-Next-80B-A3B-Instruct and by 21.4\% with GPT-5.4-nano.
