Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper
•
2510.03222
•
Published
•
74
nzy
Evernight
·
AI & ML interests
Code Generation
Recent Activity
upvoted
a
paper
about 1 month ago
Low-probability Tokens Sustain Exploration in Reinforcement Learning
with Verifiable Reward
upvoted
a
paper
7 months ago
A Minimalist Approach to LLM Reasoning: from Rejection Sampling to
Reinforce
commented on
a paper
over 1 year ago
On Leakage of Code Generation Evaluation Datasets
Organizations
None yet