Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Paper
•
2508.14029
•
Published
•
37
AI & ML interests
RLVR, LLMs, LLM Reasoning
Recent Activity
View all activity
MasterVito
authored
a
paper
about 18 hours ago
MasterVito
updated
a
dataset
3 days ago
MasterVito
published
a
dataset
3 days ago
MasterVito
authored
3
papers
2 months ago
TL;DR: Too Long, Do Re-weighting for Effcient LLM Reasoning Compression
Paper
•
2506.02678
•
Published
•
5
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Paper
•
2506.14245
•
Published
•
40
SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
Paper
•
2506.08989
•
Published
•
15