Metraipolis › archive › dc_4e220c976453

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization — arXiv:2609.32993

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32993
License (as archived)
CC0-1.0
Archived
2026-10-07T20:56:20.384Z
SHA-256 of the archived text
befa03129907bee58361e6606a1abd5ed4ab36a18f9c88928e1ea8c61ee24da9
Stable URL of this page
https://metraipolis.com/documento/dc_4e220c976453

How to cite

X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization — arXiv:2609.32993 — arXiv (en), https://arxiv.org/abs/2609.32993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e220c976453 (Metraipolis archive dc_4e220c976453, sha256 befa03129907bee58361e6606a1abd5ed4ab36a18f9c88928e1ea8c61ee24da9)
BibTeX
@misc{dc4e220c976453,
  title = {X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization — arXiv:2609.32993},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32993},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e220c976453; sha256 befa03129907bee58361e6606a1abd5ed4ab36a18f9c88928e1ea8c61ee24da9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets humans plan top-down from reusable routines. This structure sits unused, and flat training uses each scarce trajectory less fully than its content allows. Recent agents do use that structure, but only as LLM-written skills in context, never in the weights, so their gains do not generalize beyond retrieval. We instead recover this hierarchy from the data itself and train on it, with no LLM calls. Following text tokenizers, which build a vocabulary by counting alone, we score action spans by reusability and merge canonicalized actions into a reusable eXperience tree (X-Tree). Each X-Tree node captures how a frequent and success-bearing skill is composed from sub-skills, guiding efficient generalization. We integrate X-Tree into three training settings: offline RL, with each node as a training instance; online RLVR, with an adaptive skill bonus; and on-policy self-distillation, with X-Tree as the self-teacher's privileged context. Across WebArena, ScienceWorld, and WebShop at three model scales, X-Tree improves over standard recipes at matched data and budget by up to 4.5% SR on WebArena, 5.8% SR on ScienceWorld and 4.1% success on WebShop. Matched analyses attribute the gains to the X-Tree structure and the three integrations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32993 — 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 2026-10-07T20:29:01.125Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).