SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents↗ (원문, 새 창)

본문 미리보기

arXiv:2610.26995v1 Announce Type: new Abstract: LLM-based agents increasingly rely on reusable skills. However, scaling skill libraries makes efficient and accurate skill use difficult. Full skill loading incurs high token and runtime overhead. In contrast, flat semantic retrieval treats skills as independent text entries, ignoring dependencies, execution order, state transitions, and data flow constraints. We propose SPEM, a lightweight structure-aware procedural memory framework for efficient