Metraipolis › archive › dc_63b29ec415be

Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents — arXiv:2610.01787

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.01787
License (as archived): CC0-1.0
Archived: 2026-10-06T12:06:11.418Z
SHA-256 of the archived text: 782928804bc82b59212d4e0b356908e6f046e9e26ec13042a6ef53a7103b4e66
Stable URL of this page: https://metraipolis.com/documento/dc_63b29ec415be

How to cite

Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents — arXiv:2610.01787 — arXiv (en), https://arxiv.org/abs/2610.01787 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63b29ec415be (Metraipolis archive dc_63b29ec415be, sha256 782928804bc82b59212d4e0b356908e6f046e9e26ec13042a6ef53a7103b4e66)

BibTeX

@misc{dc63b29ec415be,
  title = {Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents — arXiv:2610.01787},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01787},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63b29ec415be; sha256 782928804bc82b59212d4e0b356908e6f046e9e26ec13042a6ef53a7103b4e66},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01787. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-improving GUI agents keep the trajectories they produce and return them to the agent, by fine-tuning or by retrieval into the prompt, and studies that compare the two destinations disagree. We attribute this to the unit of experience: a trajectory bundles items with different properties, so a conclusion about the bundle depends on its mix. To address this, (i) we introduce component routing, which splits the experience into locators, procedures, state facts and lessons and sends each component to the context or to the weights, compared on the same items across three backbone families, two environments and three seeds. One pool has two destinations: locators and lessons win in the weights, procedures and state facts in the context. (ii) We fit a rule in two properties measured before any training, recurrence and state-conditionality; it recovers the destination of a held-out backbone family in 24 of 24 cells, two interventions move a component toward the boundary, and routing by the rule beats every whole-trajectory baseline and, by +3.5 points on average, the better single destination of each backbone. (iii) We identify how training and producer-consumer differences change the value of the two destinations: note readout decreases after the same component is written into the weights, most for the items that recur most, context gains increase with the information gap, and weights gains decrease with the policy gap. Code and data will be released.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2610.01787 — 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 2026-10-06T10:21:27.976Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).