collaborators

8 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.AI2026

Choosing How to Remember: Adaptive Memory Structures for LLM Agents

Mingfei Lu, Mengjia Wu, Feng Liu +8

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer…

cs.LG2026

Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations

Wei Liu, Jiawei Xu, Yingru Li +4

High-quality kernel is critical for scalable AI systems, and enabling LLMs to generate such code would advance AI development. However, training LLMs for this task requires suffici…

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…

cs.LG2026

Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It

Yaxiang Zhang, Yingru Li, Jiacai Liu +4

Reinforcement Learning (RL) for training Large Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsist…