Learning to Wait: Synchronizing Agents with the Physical World
This addresses the challenge of synchronizing agents with asynchronous physical environments for scalable autonomous systems, though it is incremental as it builds on existing paradigms like Code-as-Action.
The paper tackles the problem of agents operating in real-world tasks with variable action latencies, proposing an agent-side approach that enables LLMs to predict waiting durations, which reduces query overhead and execution latency in a simulated Kubernetes cluster.
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.