CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Paper • 2508.03686 • Published • 39 •
4
Shudong Liu
Sudanl
AI & ML interests
NLP, LLM
Recent Activity
upvoted a paper 11 days ago
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI liked a model 2 months ago
moonshotai/Kimi-K2.6 upvoted a paper 5 months ago
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel GenerationsOrganizations
commented a
paper 11 months ago
It seems that the train_qa subset only contains multiple-choice questions
#4 opened about 1 year ago
by Sudanl