SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation

Apple Machine Learning Research · 2 weeks ago · 28

SCLATE was introduced as an execution substrate that lets continual-learning agent benchmarks and unmodified agents share one event scheduler, while also acting as a rollout engine that records model-call tokens and log probabilities. It compresses a month-long scenario into hours by using a hybrid simulated clock, and post-training Qwen3.5-4B cuts file-line reading by 6.8× while raising SWE-bench Verified by 16.7 points. As a result, the work enables head-to-head continual-learning evaluations and finds added memory systems do not consistently outperform native harness memory, even as a model can learn to use both harness and memory effectively.