Metraipolis › archive › dc_d117dd565a48

Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents — arXiv:2608.06171

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.06171
License (as archived): CC0-1.0
Archived: 2026-10-25T21:27:27.168Z
SHA-256 of the archived text: 1b6cf974f1cb2db979018295ce844bb6b81a17da5b04b954ee5957e262f27950
Stable URL of this page: https://metraipolis.com/documento/dc_d117dd565a48

How to cite

Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents — arXiv:2608.06171 — arXiv (en), https://arxiv.org/abs/2608.06171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d117dd565a48 (Metraipolis archive dc_d117dd565a48, sha256 1b6cf974f1cb2db979018295ce844bb6b81a17da5b04b954ee5957e262f27950)

BibTeX

@misc{dcd117dd565a48,
  title = {Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents — arXiv:2608.06171},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06171},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d117dd565a48; sha256 1b6cf974f1cb2db979018295ce844bb6b81a17da5b04b954ee5957e262f27950},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Web agents observe a browser through text, pixels, or both, and the choice is usually fixed once for all tasks. We measure six observation modes across eight site-model combinations (cells) on VisualWebArena and WebArena and ask what choosing per task would buy. The modes are complementary: each solves tasks the others miss, they fail in structurally different ways, and the best choice reverses between task sets. The obvious prize, an oracle that picks a winning mode for every task, looks large but is inflated by run-to-run noise: rerunning the same mode on the same tasks changes 12-14% of outcomes, so a second run of a mode already in hand gains about as much as adding a new one. What survives is a cost bound: sending only the tasks no mode solves to the cheapest mode cuts cost by 9.5-30.6% in 8 of 8 cells at unchanged success. We then test five routing policies (picking the mode, deciding when to spend on the strong mode, a zero-cost rule read off the task text, a confidence cascade, and pooled cost tiers), and none robustly beats simply fixing one well-chosen mode; the one exception is a fragile result in our sparsest cell. The central obstruction is that routing supervision is produced at the agent's success rate: the weaker the agent, the fewer labels a router gets, exactly where routing would be most valuable. This limit belongs to today's agents rather than to routing itself. Label supply and routing opportunity rise together (correlation 0.95 across cells), so a stronger agent can overturn the result, and we report the rerun noise bands and the full measurement protocol.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.06171 — 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 2026-10-25T21:24:38.227Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).