CUAVerifierBench
Human-annotated browser-agent trajectories for comparing automated task-success and process-quality verifiers against reviewer judgments.
Web
Reward models
Source-reviewed research and assets tagged with Reward models.
Membership follows reviewed tags; it does not establish a dependency between neighboring records. Dates preserve source precision. Annotations retain their original language.
OS-Critic Bench
A cross-platform GUI-critic benchmark with mobile, desktop and web JSONL splits and screenshot assets, accompanied by public inference and accuracy-scoring scripts.
Cross-platformDesktopWeb
WebRewardBench
An offline preference-evaluation set for web process reward models, pairing page and trajectory context with preferred and rejected candidate decisions.
Web
UI-Genie reward data
Mobile GUI reward annotations released for training UI-Genie’s trajectory-assessment model.
Android
WebPRM checklist-generation data
Web-task context, starting observations and action history paired with structured checklists and subgoal analyses for checklist generation.
Web
WebPRM Collection preference data
Checklist-annotated web decision records with page observations, prior actions, one preferred continuation and rejected alternatives for process-reward learning.
Web
GUI-G2 7B
A Qwen2.5-VL grounding checkpoint trained with Gaussian point and coverage rewards whose granularity adapts to interface-element scale.
Cross-platform
WebJudge 7B
A visual trajectory judge that retains selected intermediate screenshots to evaluate whether a web agent completed its task.
Web
WebRL outcome reward model 8B
The outcome-supervision checkpoint used by WebRL to score browser trajectories during policy training.
Web
WebShepherd 3B
A public text-based process-reward checkpoint from the Web-Shepherd collection for scoring web-agent decisions against task checklists.
Web
UI-Genie
Training and evaluation code for a mobile-agent framework that iteratively generates trajectories using agent and reward-model feedback.
Android
VEM GUI-Agent-RL
Training code that learns a value environment model from offline Android interaction data and uses its frozen value estimates to guide GUI policy optimization.
Android
Web-Shepherd inference and evaluation
Process-reward inference and benchmark-evaluation utilities that use task checklists to assess individual web-agent decisions.
Web
Showing 61–73 of 73 resources.
Get full records and evidence through the topic export manifest. Source records can be passed to the standard RAG and citation exporters after cloning the catalog.