Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal Gap} between action initiation and completion. Existing environment-side solutions, such as blocking wrappers or frequent polling, either limit scalability or dilute the agent's context window with redundant observations. In this work, we propose an \textbf{Agent-side Approach} that empowers Large Language Models (LLMs) to actively align their \textit{Cognitive Timeline} with the physical world. By extending the Code-as-Action paradigm to the temporal domain, agents utilize semantic priors and In-Context Learning (ICL) to predict precise waiting durations (\texttt{time.sleep(t)}), effectively synchronizing with asynchronous environment without exhaustive checking. Experiments in a simulated Kubernetes cluster demonstrate that agents can precisely calibrate their internal clocks to minimize both query overhead and execution latency, validating that temporal awareness is a learnable capability essential for autonomous evolution in open-ended environments.
@article{arxiv.2512.16262,
title = {Learning to Wait: Synchronizing Agents with the Physical World},
author = {Yifei She and Ping Zhang and He Liu and Yanmin Jia and Yang Jing and Zijun Liu and Peng Sun and Xiangbin Li and Xiaohe Hu},
journal= {arXiv preprint arXiv:2512.16262},
year = {2025}
}