Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling Paper • 2606.03102 • Published 1 day ago • 10
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories Paper • 2605.21468 • Published 15 days ago • 50
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling Paper • 2605.08083 • Published 27 days ago • 69
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration Paper • 2605.05566 • Published 28 days ago • 37