HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 10 天前AI 评分37
ExpVoyager：面向动态智能体技能合成的直接经验导航框架
AI 导读
ExpVoyager 将 LLM 智能体的技能合成重构为对历史经验的动态导航问题，由 skill curator 按当前任务需求在不同视图与分辨率下探索原始轨迹，边识别可复用过程知识边追踪剩余知识需求以决定下一步导航方向。实验显示其在下游任务性能上持续提升，经验空间扩大时收益持续增长，并能在高效经验访问下与现有技能兼容。
正文
Abstract:Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously learn and expand their capabilities. Within this paradigm, synthesizing the agent skill has emerged as a promising solution for transforming accumulated experience into reusable procedural knowledge, serving as an important layer for the harness system that supplies agents at runtime. Despite its potential, existing approaches largely abstract past experience into fixed procedural knowledge before downstream demands are known, which risks discarding knowledge that later becomes critical while retaining instance-specific details irrelevant to future tasks. In this paper, we reframe agent skill synthesis as a dynamic navigation problem over past experience, where agents actively explore accumulated trajectories on demand for the current task with targeted and fine-grained access to experience knowledge. To this end, we propose ExpVoyager, a novel framework in which a skill curator navigates raw experience across different views and resolutions, continually identifying reusable procedural knowledge from what it observes while tracking remaining knowledge needs that guide where to navigate next. Extensive experiments demonstrate both the effectiveness and versatility of ExpVoyager, showing consistent improvements in downstream task performance, continual gains as the experience space scales, and practical compatibility with existing skills under efficient experience access.
| Comments: | Work in Progress |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.32630 [cs.CL] |
| (or arXiv:2609.32630v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.32630 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kwangwook Seo [view email]
[v1]
Sat, 26 Sep 2026 13:48:10 UTC (11,182 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org