No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Paper
•
2509.21880
•
Published
•
39
•
2
Thanh-Long V. Le
bltnynk
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 10 hours ago
Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement
Learning
commented on
a paper
11 days ago
No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM
Reinforcement Learning via Entropy-Guided Advantage Shaping
Organizations
None yet
