Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
Paper
•
2505.15277
•
Published
•
97
hyojun
hyojuuun
AI & ML interests
NLP
Recent Activity
upvoted
a
paper
6 days ago
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
published
a model
2 months ago
hyojuuun/Science-RLVR-PPO-Multiple-Choice
published
a model
2 months ago
hyojuuun/Science-RLVR-PPO
Organizations
None yet
hyojuuun's activity
upvoted
a
paper
6 days ago
upvoted
3
articles
3 months ago
Article
DABStep: Data Agent Benchmark for Multi-step Reasoning
By
and 5 others
•
•
88
Article
Open-source DeepResearch – Freeing our search agents
By
and 4 others
•
•
1.25k
Article
Open-R1: a fully open reproduction of DeepSeek-R1
By
and 2 others
•
•
861