Metraipolis › archive › dc_6ebd43774b91
SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents — arXiv:2608.12429
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12429
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:17:57.363Z
- SHA-256 of the archived text
72faf47b4c3cb9f4bbe59a2752b3a0788e21a231cb882450e77213830d74ef43- Stable URL of this page
https://metraipolis.com/documento/dc_6ebd43774b91
How to cite
SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents — arXiv:2608.12429 — arXiv (en), https://arxiv.org/abs/2608.12429 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ebd43774b91 (Metraipolis archive dc_6ebd43774b91, sha256 72faf47b4c3cb9f4bbe59a2752b3a0788e21a231cb882450e77213830d74ef43)
BibTeX
@misc{dc6ebd43774b91,
title = {SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents — arXiv:2608.12429},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12429},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ebd43774b91; sha256 72faf47b4c3cb9f4bbe59a2752b3a0788e21a231cb882450e77213830d74ef43},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12429. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Web agents often struggle to generalize to unseen websites because they lack website-specific supervision. Recent exploration-based data synthesis methods reduce manual annotation, but they still face two key limitations: they often fail to cover the full functionality of a website, and without sufficient website prior knowledge, they tend to propose hallucinated tasks, which in turn limits the diversity and efficiency of downstream trajectory synthesis. We present \textbf{SynWeaver}, a website-prior task-trajectory co-synthesis framework designed to address these challenges. SynWeaver first performs structured website exploration and constructs a website map that covers a broad set of functionally distinct page states and executable interactions on the target website. It then derives page-level and transition-level supervision from this map to train a UI-aware model with website-specific priors, enabling more grounded task proposals. Finally, SynWeaver performs collaborative task-trajectory synthesis, jointly updating the task and execution trajectory when they become inconsistent, and then verifies and repairs the collected results to produce executable, semantically aligned supervision. Experiments on WebArena and WebVoyager demonstrate that SynWeaver consistently outperforms strong synthesis baselines and yields more effective supervision for both in-domain and out-of-domain generalization.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.12429 — 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 2026-10-19T04:13:06.667Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).