3 papers
cs.LG2026
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
Yingru Li, Jiacai Liu, Jiawei Xu +4
Policy gradient methods for Large Language Models optimize a policy via a surrogate objective computed from samples of a rollout policy . However, modern…
cs.LG2026
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
Yingru Li, Jiawei Xu, Ziniu Li +10
Reinforcement Learning (RL) for Large Language Models (LLMs) often suffers from training collapse in long-horizon tasks due to exploding gradient variance. To mitigate this, a base…
cs.LG2026
Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail
Yingru Li, Jiawei Xu, Jiacai Liu +6
Reinforcement Learning (RL) for Large Language Models (LLMs) faces a fundamental tension: the numerical divergence between high-throughput inference engines and numerically precise…