Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Paper
•
2505.04842
•
Published
•
12
•
3
Arian Hosseini
arianhosseini
·
AI & ML interests
large language models, reasoning, planning, systematic generalization
Recent Activity
authored
a paper
about 2 months ago
Deep Language Networks: Joint Prompt Training of Stacked LLMs using
Variational Inference
authored
a paper
about 2 months ago
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR
Summarization
authored
a paper
about 2 months ago
Generative Verifiers: Reward Modeling as Next-Token Prediction
Organizations
commented
a
paper
6 months ago