---
id: 20261022-T0-11
title: "SPEM：给LLM Agent装上结构化程序记忆，技能多了也能快速调用"
title_en: "SPEM Gives LLM Agents Structure-Aware Procedural Memory for Skill Retrieval"
url: https://ai.daily.yangsir.net/daily/20261022-T0-11
issue_date: 2026-10-22
publish_date: 2026-10-21T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.26995
---

# SPEM：给LLM Agent装上结构化程序记忆，技能多了也能快速调用

随着LLM Agent依赖的可复用技能库不断扩大，准确高效地调用技能变得困难：完整加载技能会带来高昂的token和运行开销，而扁平的语义检索又把技能当作孤立条目处理。SPEM提出结构感知的程序记忆方案，利用技能之间的结构关系来检索和复用技能。该方案面向技能库规模增长后的效率问题，可用于需要大量工具和技能组合的Agent系统。

## English Version

**SPEM Gives LLM Agents Structure-Aware Procedural Memory for Skill Retrieval**

LLM agents increasingly rely on reusable skills, but scaling skill libraries makes efficient and accurate skill use hard: full skill loading incurs high token and runtime overhead, while flat semantic retrieval treats skills as isolated items. SPEM proposes structure-aware procedural memory that exploits relationships among skills for retrieval and reuse. The approach targets efficiency as skill libraries grow and applies to agent systems that combine many tools and skills.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.26995)

**详情页**：https://ai.daily.yangsir.net/daily/20261022-T0-11

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*