让大模型学会等待，精准同步物理世界的时间节奏。
Learning to Wait: Synchronizing Agents with the Physical World
- 用代码指令预测等待时长，让智能体主动对齐真实时间
- 在模拟集群中降低查询开销和执行延迟，效果显著提升
- 适合需要异步交互的自主系统开发与优化
现实世界的代理任务不同于同步的马尔可夫决策过程，常涉及非阻塞动作和可变延迟，造成动作发起与完成之间的根本性「时间鸿沟」。现有环境侧解决方案如阻塞包装器或频繁轮询，要么限制可扩展性，要么因冗余观测稀释智能体上下文窗口。本文提出一种代理端方法，使大语言模型（LLMs）能够主动将其「认知时间线」与物理世界对齐。通过将代码即动作范式拓展至时间维度，代理利用语义先验和上下文学习（ICL）预测精确等待时长（time.sleep(t)），在无需反复检查的情况下实现与异步环境的有效同步。在模拟Kubernetes集群中的实验表明，代理能精准校准内部时钟，同时最小化查询开销与执行延迟，验证了时间感知是一种可学习的关键能力，对开放环境中自主演化至关重要。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。