Web-Shepherd: Advancing PRMs for Reinforcing Web Agents - a LangAGI-Lab Collection

LangAGI-Lab 's Collections

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Coffee-Gym: An Environment for Evaluating and Improving Natu

Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback

Cactus: Towards Psychological Counseling Conversations

Web Agents with World Models

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

updated May 22

LangAGI-Lab/WebShepherd_8B

Feature Extraction • Updated May 22 • 23 • 4
LangAGI-Lab/WebShepherd_3B

Feature Extraction • Updated May 22 • 36 • 1
LangAGI-Lab/WebPRMCollection_preference_pair

Viewer • Updated May 22 • 9.46k • 156
LangAGI-Lab/WebRewardBench

Viewer • Updated May 22 • 776 • 41
LangAGI-Lab/WebPRMCollection_checklist_generation

Viewer • Updated May 19 • 3.63k • 45
LangAGI-Lab/WebShepherd_checklist_generation_only_8B

Feature Extraction • Updated May 19 • 13 • 1
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Paper • 2505.15277 • Published May 21 • 101