CUAVerifierBench
Human-annotated browser-agent trajectories for comparing automated task-success and process-quality verifiers against reviewer judgments.
网页
奖励模型
已审阅并标注「奖励模型」的研究与资产。
条目依据已审阅标签归类，同一主题不表示资源之间存在依赖关系。日期保留来源精度，注释保留原语言。
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.
跨平台桌面网页
WebRewardBench
An offline preference-evaluation set for web process reward models, pairing page and trajectory context with preferred and rejected candidate decisions.
网页
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.
网页
WebPRM Collection preference data
Checklist-annotated web decision records with page observations, prior actions, one preferred continuation and rejected alternatives for process-reward learning.
网页
GUI-G2 7B
A Qwen2.5-VL grounding checkpoint trained with Gaussian point and coverage rewards whose granularity adapts to interface-element scale.
跨平台
WebJudge 7B
A visual trajectory judge that retains selected intermediate screenshots to evaluate whether a web agent completed its task.
网页
WebRL outcome reward model 8B
The outcome-supervision checkpoint used by WebRL to score browser trajectories during policy training.
网页
WebShepherd 3B
A public text-based process-reward checkpoint from the Web-Shepherd collection for scoring web-agent decisions against task checklists.
网页
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.
网页
第 61–73 条，共 73 条资源。
通过主题导出清单获取完整记录和证据。克隆目录后，可将主题记录直接交给标准 RAG 与引用导出工具。