Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Paper
•
2508.14029
•
Published
•
27
Xiao Liang
MasterVito
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 8 hours ago
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with
Adaptive Exploration
authored
a paper
about 15 hours ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
upvoted
a
paper
about 18 hours ago
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains
RLVR
Organizations
authored
a
paper
about 15 hours ago
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