Metraipolis › archive › dc_3406f077dc2d

Interpretable Early Termination of Web Navigation Agents via Closed Sequential Pattern Mining — arXiv:2611.04142

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04142
License (as archived)
CC0-1.0
Archived
2026-11-04T11:50:14.667Z
SHA-256 of the archived text
ab5fd3330538f212c5cfec5936bc67f725b6140e931a7fc821b6b52d40dfcf1c
Stable URL of this page
https://metraipolis.com/documento/dc_3406f077dc2d

How to cite

Interpretable Early Termination of Web Navigation Agents via Closed Sequential Pattern Mining — arXiv:2611.04142 — arXiv (en), https://arxiv.org/abs/2611.04142 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3406f077dc2d (Metraipolis archive dc_3406f077dc2d, sha256 ab5fd3330538f212c5cfec5936bc67f725b6140e931a7fc821b6b52d40dfcf1c)
BibTeX
@misc{dc3406f077dc2d,
  title = {Interpretable Early Termination of Web Navigation Agents via Closed Sequential Pattern Mining — arXiv:2611.04142},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04142},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3406f077dc2d; sha256 ab5fd3330538f212c5cfec5936bc67f725b6140e931a7fc821b6b52d40dfcf1c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04142. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Web navigation agents built on open-weight language models fail often and fail late, with most of the tokens spent after the trajectory has become unrecoverable. Recent work has shown that early termination is a viable cost-reduction strategy, but existing approaches produce opaque termination decisions that do not support diagnosis or human oversight. In this work we apply closed sequential pattern mining (BIDE+) to K-step prefixes of agent execution traces to produce a small, human-reviewable failure-signature library that organizes into a four-category failure taxonomy with associated repair recommendations. We use a multi-variant evaluation protocol that explicitly removes contamination artifacts (zero-step crashes and trivially separable single-step successes) so that reported detection accuracy reflects behavioral discrimination rather than trace-length distributions. We evaluate our methodology on 1,544 MiniWoB++ traces collected from three open-weight language models, achieving the best F1 at K=3 on the Exclude-errors configuration across eight methods (0.717), recovering 88% of test-set failures within three steps, and supporting an early-termination policy that saves 26.3% of tokens at 92% precision.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.04142 — 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 2026-11-04T11:50:11.433Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).