Metraipolis › archive › dc_fbe11e7bdabd
DynaRev: Benchmarking Web Agents under Dynamic Goal Revision — arXiv:2610.40133
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40133
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:10:39.070Z
- SHA-256 of the archived text
c4dde5d6fe230cd5ff3a295c0070f677684f809ce1a71b1031037b1e6dc69940- Stable URL of this page
https://metraipolis.com/documento/dc_fbe11e7bdabd
How to cite
DynaRev: Benchmarking Web Agents under Dynamic Goal Revision — arXiv:2610.40133 — arXiv (en), https://arxiv.org/abs/2610.40133 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbe11e7bdabd (Metraipolis archive dc_fbe11e7bdabd, sha256 c4dde5d6fe230cd5ff3a295c0070f677684f809ce1a71b1031037b1e6dc69940)
BibTeX
@misc{dcfbe11e7bdabd,
title = {DynaRev: Benchmarking Web Agents under Dynamic Goal Revision — arXiv:2610.40133},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40133},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbe11e7bdabd; sha256 c4dde5d6fe230cd5ff3a295c0070f677684f809ce1a71b1031037b1e6dc69940},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40133. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Web agents are typically evaluated with goals fully specified before execution and fixed thereafter, whereas real users often revise their requirements during interaction. To study such interactions, we introduce DynaRev, a benchmark of 181 tasks to evaluate web agents under dynamic goal revision. DynaRev uses semantic milestones to deliver revisions at task-defined stages, covers additive revisions, unconditional overrides, and runtime-conditioned overrides, and evaluates correctness, responsiveness, and efficiency through trajectory-grounded evaluation. Five-model evaluations show that agents often satisfy only part of the task requirements, with performance varying across task sources, revision types, and models. Further analyses reveal varied milestone timing, mixed effects of dynamic delivery, and contrasting revision-handling outcomes, with gains from instruction rewriting while preserving browser state and losses from browser resets. DynaRev provides a testbed for studying how web agents adapt to evolving user goals. The code and data are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.40133 — 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 2026-10-31T06:07:08.550Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).