VisCritic: Visual State Comparison as Process Reward for GUI Agents

arXiv:2606.24525 · cs.CV · Submitted 2026-06-23 · Read on arXiv

cs.CV

Submitted: 2026-06-23

Updated: 2026-06-23

Comments: 17 pages, 4 figures; ECCV 2026 submission; supplementary material uploaded as ancillary file

Journal ref: Computer Vision - ECCV 2026. LNCS vol 17026, pp. 654-670. Springer, Cham

DOI: 10.1007/978-3-032-37595-7_36

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 44× in this paper · explained in 2 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Grounding — 9× in this paper · explained in 3 episodes
• alpha — 7× in this paper
• Accuracy — 6× in this paper · explained in 1 episode
• Visual Difference Encoder — 6× in this paper
• Visual Grounding — 5× in this paper · explained in 2 episodes
• World Model — 5× in this paper · explained in 7 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Vision-language models — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 3 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Task Decomposition — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper
• Contrastive Learning — 1× in this paper · explained in 7 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Graphical User Interface — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Modality Gap — 1× in this paper · explained in 6 episodes
• Predictive Coding — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 4 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 5 episodes

Sources

• MobileDreamer: Generative Sketch World Model for GUI Agent
• GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition
• Computer-Using World Model
• Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
• CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks
• Representation Learning with Contrastive Predictive Coding
• GPT-4 Technical Report
• Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning
• Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations
• Qwen2.5-VL Technical Report
• Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents
• Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
• GUI-PRA: Process Reward Agent for GUI Tasks
• Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
• Adaptive Milestone Reward for GUI Agents

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models