Xing-Cheng Zhang

Belayer: Efficient Fault Tolerance for LLM Agentic RL Training

Belayer handles failures in both rollout engines and environment execution while targeting low failure-free overhead, and shows low measured overhead during failure-free training, a worker-recovery-time reduction of up to 42 times faster compared with a full engine cold start, and 1.5 to 3.5 times faster recovery from...