3 papers
cs.AI2026
Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learning
Zhuoming Chen, Hongyi Liu, Yang Zhou +2
Reinforcement learning (RL) for large language models (LLMs) remains expensive, particularly because the rollout is expensive. Decoupling rollout generation from policy optimizatio…
cs.LG2025
Kinetics: Rethinking Test-Time Scaling Laws
Ranajoy Sadhukhan, Zhuoming Chen, Haizhong Zheng +3
We rethink test-time scaling laws from a practical efficiency perspective, revealing that the effectiveness of smaller models is significantly overestimated. Prior work, grounded i…
cs.AI2025
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Haizhong Zheng, Yang Zhou, Brian R. Bartoldson +4
Reinforcement learning, such as PPO and GRPO, has powered recent breakthroughs in LLM reasoning. Scaling rollout to sample more prompts enables models to selectively use higher-qua…