Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR
Paper
•
2509.23808
•
Published
•
47
wuliwuliy
wuliwuliy
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
Organizations
None yet