Metraipolis › archive › dc_df2389ba6f07

ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis — arXiv:2609.32630

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32630
License (as archived)
CC0-1.0
Archived
2026-10-07T21:50:15.232Z
SHA-256 of the archived text
afd12634ff8a221272c536e2f1dedca2fd7c9d1371121f1e41c03eb7113af3a8
Stable URL of this page
https://metraipolis.com/documento/dc_df2389ba6f07

How to cite

ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis — arXiv:2609.32630 — arXiv (en), https://arxiv.org/abs/2609.32630 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df2389ba6f07 (Metraipolis archive dc_df2389ba6f07, sha256 afd12634ff8a221272c536e2f1dedca2fd7c9d1371121f1e41c03eb7113af3a8)
BibTeX
@misc{dcdf2389ba6f07,
  title = {ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis — arXiv:2609.32630},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32630},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df2389ba6f07; sha256 afd12634ff8a221272c536e2f1dedca2fd7c9d1371121f1e41c03eb7113af3a8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32630. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.32630 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T21:27:08.457Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).