# Learning to Wait: Synchronizing Agents with the Physical World

arXiv: https://arxiv.org/abs/2512.16262 · HTML: https://mlsanity.com/paper/2512.16262/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 11 of 11)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [TempoRL: Learning When to Act](https://mlsanity.com/paper/2106.05262/) (2021)
- [Active Reinforcement Learning: Observing Rewards at a Cost](https://mlsanity.com/paper/2011.06709/) (2020)
- [KubeIntellect: A Modular LLM-Orchestrated Agent Framework for End-to-End Kubernetes Management](https://mlsanity.com/paper/2509.02449/) (2025)
- [Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning](https://mlsanity.com/paper/2307.02620/) (2023)
- [Density estimation on small datasets](https://mlsanity.com/paper/1804.01932/) (2018)
- [On fitting the Lomax distribution: a comparison between minimum distance estimators and other estimation techniques](https://mlsanity.com/paper/2207.06086/) (2022)

## Abstract (arXiv)

Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental textitTemporal 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 Agent-side Approach that empowers Large Language Models (LLMs) to actively align their textitCognitive 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 (texttttime.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.