Metraipolis › archive › dc_6fa7aaadb30a
VeriCUA: Verification as Agentic Exploration for Computer-Using Agents — arXiv:2610.40578
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40578
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:10:54.450Z
- SHA-256 of the archived text
ddab95949e1988dc41a5665620fe086b6f68249f7f0db9a30af9e710b1447a45- Stable URL of this page
https://metraipolis.com/documento/dc_6fa7aaadb30a
How to cite
VeriCUA: Verification as Agentic Exploration for Computer-Using Agents — arXiv:2610.40578 — arXiv (en), https://arxiv.org/abs/2610.40578 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6fa7aaadb30a (Metraipolis archive dc_6fa7aaadb30a, sha256 ddab95949e1988dc41a5665620fe086b6f68249f7f0db9a30af9e710b1447a45)
BibTeX
@misc{dc6fa7aaadb30a,
title = {VeriCUA: Verification as Agentic Exploration for Computer-Using Agents — arXiv:2610.40578},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40578},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6fa7aaadb30a; sha256 ddab95949e1988dc41a5665620fe086b6f68249f7f0db9a30af9e710b1447a45},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40578. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation, and reinforcement learning. Typical automated approaches prompt vision-language models (VLMs) to judge trajectories or generate programs to inspect application state. However, both rely on partial views of complex digital environments. VLM judges are restricted to supplied observations, while generated programs depend on accessible state. These views can omit decisive evidence or leave completion judgments unsupported. Tailoring separate verifiers to different platforms and access settings adds further engineering cost. We present VeriCUA, a platform-agnostic framework for verification through agentic exploration. It treats verification as dynamic evidence gathering and assessment within a shared procedure for online and offline settings across platforms and observation modalities. After inspecting the available context to construct a task rubric, the verifier selects GUI or code checks for unresolved requirements and combines their findings under explicit evidence rules. Experiments show improved agreement with reference labels over the compared baselines across these settings, with the largest offline gains on hard cases and stronger rejection of false completion claims online. Further analyses connect these gains to complementary evidence and test-time exploration. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.40578 — 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 2026-10-31T06:07:08.574Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).