ReMix brings off-policy reinforcement finetuning to LLM post-training by reusing rollout data from past policies, dramatically reducing training cost while staying competitive on math reasoning benchmarks.
Jan 5, 2026
DistRLVR is a distributional RL framework for LLM post-training with verifiable rewards that models token-level return distributions and uses tail-aware advantages to improve sample efficiency and reasoning performance.
Jan 1, 2026