2 papers
cs.DC2026
Scheduling Mixed RL Rollouts Beyond Prefix Locality
Zetao Hong, Song Yuan, Yuanhao Ding +4
Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple domains and feedback paradigms. P…
cs.LG2026
MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training
Yikai Wang, Chuansai Zhou, Yuhang Zhou +10
Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging overhead. In…