AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

VisCritic: Visual State Comparison as Process Reward for GUI Agents

Jiachen Qian

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Change Region Attention (ablation)VisCritic · AndroidWorld ablation (ShowUI base)success rate: 23.4 -> 24.8Improved
add multi-task head over success-only prediction (ablation)VisCritic · AndroidWorld ablation (ShowUI base)success rate: 24.1 -> 24.8Improved
add contrastive pre-training (ablation)VisCritic · AndroidWorld ablation (ShowUI base)success rate: 22.0 -> 24.8Improved
add post-execution verification (ablation)VisCritic · AndroidWorld ablation (ShowUI base)success rate: 21.4 -> 24.8Improved
use learned VDE instead of pixel-level differences (ablation)VisCritic · AndroidWorld ablation (ShowUI base)success rate: 21.2 -> 24.8Improved
visual state comparison instead of textual critic (ablation)Critic head · AndroidWorld + Mind2Web verificationF1: 66.2 -> 84.6Improved
visual features instead of pixel difference (ablation)Critic head · AndroidWorld + Mind2Web verificationF1: 70.5 -> 84.6Improved
add VisCritic to ShowUIShowUI · WebArenatask SR: 17.6 -> 23.2Improved
add VisCritic to Qwen2.5-VL agent vs text critic on OSWorldQwen2.5-VL Agent · OSWorldtask SR: 17.4 -> 17.1Hurt
add VisCritic to SeeClickSeeClick · Mind2Webstep SR: 33.4 -> 37.6Improved
swap InternViT-6B for SigLIP-400M backbone (ablation)VisCritic · AndroidWorldF1: 80.3% F1 and 23.1% task SRMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy