Metraipolis › archive › dc_6e84e26b83bb
Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks — arXiv:2610.22539
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22539
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:48:19.940Z
- SHA-256 of the archived text
be77c53ffa474aa1ffc6a8d19073454c9ca4bc814549e93fcfd016fa522b450b- Stable URL of this page
https://metraipolis.com/documento/dc_6e84e26b83bb
How to cite
Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks — arXiv:2610.22539 — arXiv (en), https://arxiv.org/abs/2610.22539 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e84e26b83bb (Metraipolis archive dc_6e84e26b83bb, sha256 be77c53ffa474aa1ffc6a8d19073454c9ca4bc814549e93fcfd016fa522b450b)
BibTeX
@misc{dc6e84e26b83bb,
title = {Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks — arXiv:2610.22539},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22539},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e84e26b83bb; sha256 be77c53ffa474aa1ffc6a8d19073454c9ca4bc814549e93fcfd016fa522b450b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22539. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The web is not static or uniform. Websites that serve the same purpose can look and navigate very differently. Even within a single site, successive redesigns can change how familiar features are presented and accessed. Humans adapt to this by recognizing familiar interaction patterns and reusing what they already know. We give web agents a similar ability with WebMix, a mixture hypernetwork that adapts them to unseen interfaces by composing previously trained low-rank adapters. WebMix begins with a bank of adapters trained on source interfaces. At deployment, a scout agent explores the target interface and summarizes its observations into a compact manual. A lightweight router uses this manual to predict mixing coefficients over the adapter bank, which combine the existing adapters into a new one for inference. Adapting to a new interface takes only a scouting run and a forward pass, without gradient updates on the target. With Qwen and Llama models, we evaluate domain transfer on TimeWarp and WebArena-Lite-v2, and version transfer on TimeWarp. In all three settings, WebMix matches or outperforms in-context learning and LoRA baselines, often matching the average success of specialists trained directly on those interfaces. On TimeWarp domain transfer, it gains about 8 percentage points on average over the best baseline with both models. These gains do not come at the cost of seen interfaces, where WebMix keeps its lead, and extend to version transfer. Adapting to a new interface can therefore rely on exploration and composition instead of retraining. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.22539 — 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 2026-10-19T08:42:40.212Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).