StatePortal: Agentic Checkpoint Synthesis for Testing Deep States in Interactive Software
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 https://github.com/pzy2000/State_Portal and website at https://stateportal.mineyosemite.chatgpt.site
Community
Why replay long interaction sequences just to test deep states?
๐ StatePortal uses AI agents to synthesize reusable checkpoints, making deep-state testing faster and more scalable.
The hybrid check is the part I care about: a restored state can pass its assertions and still look wrong. Do you revalidate checkpoints after code changes, or were the 1,361 replays all against the same application revision?
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- HerAgent: A Block-Level Checkpointing Harness for Coding-Agent Environment Setup (2026)
- Harnesses That Improve Themselves: A Unifying Framework for Self-Improving Agent Harnesses (2026)
- Understanding Tool-Mediated Interaction Failures in Agentic GUI Software: An Empirical Study (2026)
- FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration (2026)
- Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected? (2026)
- A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain (2026)
- Zero2Repo: Can Coding Agents Build Repositories from Scratch? (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.23257 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper