VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation

arXiv:2604.21375 · cs.CL, cs.AI, cs.SE · Submitted 2026-04-23 · Read on arXiv

cs.CL, cs.AI, cs.SE

Submitted: 2026-04-23

Updated: 2026-09-24

Code: https://github.com/UCSC-VLAA/VLAA-GUI

Project page: https://ucsc-vlaa.github.io/VLAA-GUI

Terminology

• Verifier — 79× in this paper · explained in 2 episodes
• Grounding — 27× in this paper · explained in 3 episodes
• Verification — 21× in this paper · explained in 2 episodes
• Benchmark — 19× in this paper · explained in 2 episodes
• Ablation — 13× in this paper · explained in 1 episode
• Accuracy — 7× in this paper · explained in 1 episode
• Action Space — 5× in this paper · explained in 1 episode
• Procedural Knowledge — 5× in this paper · explained in 2 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Agentic Framework — 3× in this paper · explained in 6 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Visual Grounding — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Graphical User Interface — 2× in this paper
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 13 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Standardized Benchmarks — 1× in this paper · explained in 2 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Agent S: An Open Agentic Framework that Uses Computers Like a Human
• Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
• Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
• ScreenAI: A Vision-Language Model for UI and Infographics Understanding
• Qwen3-VL Technical Report
• Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
• Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
• Why Do Multi-Agent LLM Systems Fail?
• A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation
• Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints
• SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
• The BrowserGym Ecosystem for Web Agent Research
• Training Verifiers to Solve Math Word Problems
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
• WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
• Mano Technical Report
• Scaling Agents for Computer Use
• A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
• OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering