SCLATE platform improves testing and training of continual-learning AI agents

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

Artificial IntelligenceDistributed, Parallel, and Cluster ComputingMachine Learning

Summary

Continual-learning AI agents need to be tested and trained over many sessions with different tasks and breaks. The authors created SCLATE, a system that can schedule all these activities together on one timeline, making it easier to run month-long tests in just hours. They showed that adding extra memory to agents does not always help and that different AI models use memory in very different ways. They also improved a model’s performance by training it with various memory setups without changing the original training code.

What this means in practice

  • For machine learning engineers: Run long-term training and evaluation scenarios for continual-learning agents using a unified scheduler to integrate tasks and agent events with time compression.
  • For ai platform developers: Integrate unmodified AI agents and benchmarks into a shared event-driven system that records detailed model call data without code changes.

Authors

Youngmok Jung, Sirajul Salekin, Henry Tran, Javier Movellan, Zhao Huang, Manjot Bilkhu

Abstract

Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with agent-side events such as session stop and start, crons, and memory consolidation. Yet existing benchmarks and training frameworks schedule only the benchmark's own events, leaving each benchmark and agent pair to build a custom scheduling loop. We present SCLATE, an execution substrate where benchmarks and unmodified agents each add their events to one open event scheduler through an adapter. A hybrid simulated clock runs these events on a shared timeline, flowing in real time while the agent works and skipping idle gaps, which compresses a month-long scenario into hours. SCLATE also serves as a rollout engine that runs any agent's harness and memory unmodified, recording the tokens and log probabilities of every model call through an in-container proxy. We port seven benchmarks to SCLATE and compare ten unmodified harness and memory configurations head to head on ten models. The comparison shows that an added memory system does not reliably beat the harness's native memory and that models differ widely in how they use the same harness and memory. We then post-train Qwen3.5-4B through unmodified harnesses and memory systems. The model learns to use both, reading 6.8x fewer file lines with a 16.7-point higher SWE-bench Verified pass rate, and writing richer memory records, while its held-out MetaClaw accuracy rises by up to 11.8 points.