跳到正文
arXiv cs.AI· Zhiyuan Peng (Shanghai Jiao Tong University), Wei Tao (LIGHTSPEED), Chenhao Ying (Shanghai Jiao Tong University), Yuan Luo (Shanghai Jiao Tong University), Yiwen Guo (Independent Researcher)·· 1 小时前AI 评分45

StatePortal:面向交互式软件深度状态测试的智能体检查点合成方法

StatePortal: Agentic Checkpoint Synthesis for Testing Deep States in Interactive Software

AI 导读

StatePortal 是一种智能体方法,可从自然语言功能测试用例和只读源码访问中合成检查点,用于测试需要长交互历史的交互式软件深度状态。它通过一次绑定的应用钩子恢复状态,并采用程序状态与视觉混合双 oracle 评分。

正文 · 原文

View PDF HTML (experimental)

Abstract:Large language models have reduced the effort to generate code for interactive software with graphical user interfaces (GUIs). For such software, a key testing bottleneck is reaching a deep state, one that requires a long interaction history. The cost of reaching it recurs across commits, and the GUI automation that could amortize it assumes a DOM or accessibility tree that self-rendered engines do not expose. We introduce StatePortal, an agent that synthesizes a checkpoint, an artifact that restores that state and can be versioned and replayed, from a natural-language functional test case and read-only access to the target's source code. The checkpoint is restored through a per-application hook that an onboarding agent binds or synthesizes once without hand-written hook code. Because a checkpoint can satisfy state checks while rendering incorrectly, checkpoints are scored by hybrid programmatic-state and visual evaluation: acceptance requires both a programmatic-state oracle and a visual oracle to pass. We calibrate the visual oracle against a blinded cross-VLM reference. We release DeepStateBench, 61 deep-state tasks across 10 interactive applications that span five language families and six rendering stacks, with source sizes from 874 to 7.2M lines. Across three registered models, a GUI agent seeded with synthesized checkpoints completes 10.4% of trials, compared with 0% without seeding under the same pixel action space, while StatePortal, which also delivers the target action through the hook, completes 27.5%. Over 1,361 replays of 112 checkpoints, 98.90% reproduce the original verdict with zero model calls, and the hybrid oracle detects 96.25% (77/80) of controlled visual faults invisible to programmatic-state checks alone. We open-source our code at this https URL and website at this https URL
Comments: submitted to ICLR 2027
Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.23257 [cs.SE]
  (or arXiv:2611.23257v1 [cs.SE] for this version)
  https://doi.org/10.48550/arXiv.2611.23257

arXiv-issued DOI via DataCite

Submission history

From: Zhiyuan Peng [view email]
[v1] Tue, 29 Sep 2026 17:55:57 UTC (5,785 KB)

来源:arXiv cs.AI · arxiv.org