arXiv cs.AI· Qiushi Sun, Da Yu, Alexander Knop, Amer Sinha, Lingpeng Kong, Ben Kao, Ravi Kumar, Pritish Kamath·· 2 小时前AI 评分48
VeriCUA：用智能体探索实现计算机使用智能体的任务验证
VeriCUA: Verification as Agentic Exploration for Computer-Using Agents
AI 导读
arXiv 论文提出 VeriCUA，一个平台无关的验证框架，将验证视为动态的证据收集与评估，用同一流程覆盖桌面、移动和网页环境下计算机使用智能体（CUA）的在线与离线设置。验证器在检查上下文并构建任务 rubric 后，为未决需求选择 GUI 或代码检查，并按明确的证据规则综合结果。实验显示其与参考标签的一致性优于对比基线，离线困难案例提升最大，在线更能拒绝虚假完成声明。
正文 · 原文
Abstract: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.
| Comments: | Work in progress |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.40578 [cs.AI] |
| (or arXiv:2610.40578v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40578 arXiv-issued DOI via DataCite |
Submission history
From: Qiushi Sun [view email]
[v1]
Thu, 29 Oct 2026 17:45:26 UTC (4,118 KB)
来源：arXiv cs.AI · arxiv.org