HyperSkill：基于超图结构技能记忆的自进化大语言模型智能体

中文摘要 AI 辅助

随着智能体任务复杂度不断提升，大语言模型（LLM）智能体愈发依赖经验记忆来跨任务复用过程性知识。有效的记忆设计需同时解决存储内容、记忆结构与检索方式、记忆进化这三个核心问题，而现有系统仅部分处理各问题：它们将轨迹、洞见或工作流存储为孤立条目，忽略子任务与可复用技能间的组合关系；通过平面嵌入相似度检索，未利用关系信号；维护记忆时未借助其关系结构。本文提出HyperSkill，一种基于超图的记忆框架，可同时改进上述三个方面。HyperSkill将记忆表示为含两类节点的超图：子任务步骤与可复用技能，每条超边关联来自单条轨迹的子任务与技能。双路径检索同时查询子任务与轨迹层级，通过检索轨迹间的共现关系对技能排序。定期的结构感知维护会修剪低效用节点，并通过质量加权传播合并冗余技能。在xBench、GAIA、WebWalkerQA数据集上，使用GPT-4o与Qwen3-30B-A3B模型，HyperSkill的性能优于10种记忆基线方法，在GAIA上提升最高达11.51，在WebWalkerQA上提升最高达11.18。

英文摘要

As agentic tasks grow in complexity, LLM agents increasingly rely on experiential memory to reuse procedural knowledge across tasks. Effective memory design must jointly address what to store, how memory is structured and retrieved, and how memory evolves. Existing systems tackle each only partially: they store trajectories, insights, or workflows as isolated entries, discarding compositional relationships among subtasks and reusable skills; retrieve by flat embedding similarity that ignores relational signals; and maintain memory without leveraging its relational structure. We propose HyperSkill, a hypergraph-based memory framework that jointly improves all three. HyperSkill represents memory as a hypergraph with two node types, subtask steps and reusable skills, where each hyperedge links the subtasks and skills from a single trajectory. Dual-path retrieval queries both subtask and trajectory levels, ranking skills by co-occurrence across retrieved trajectories. Periodic structure-informed maintenance prunes low-utility nodes and merges redundant skills via quality-weighted propagation. Across xBench, GAIA, and WebWalkerQA with GPT-4o and Qwen3-30B-A3B, HyperSkill outperforms ten memory baselines, yielding gains of up to +11.51 on GAIA and +11.18 on WebWalkerQA.

发表机构

• University of Southern California（南加州大学）
• University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
• Northwestern University（西北大学）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

25 pages