OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published Jun 25 • 47
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation Paper • 2509.15194 • Published Sep 18 • 33
Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness Paper • 2505.22960 • Published May 29 • 16
