Discrete Minds in a Continuous World: Do Language Models Know Time Passes?

TL;DR

This paper explores whether large language models can perceive and adapt to the passage of real-world time, demonstrating their partial awareness through experiments on timing, response adaptation, and dynamic environment navigation.

Contribution

It introduces the Token-Time Hypothesis and develops the BombRush challenge to assess and demonstrate LLMs' temporal awareness and adaptability in time-sensitive tasks.

Findings

LLMs can map token counts to real-world time.

LLMs adapt response length based on perceived urgency.

Model size and reasoning skills influence temporal awareness.

Abstract

While Large Language Models (LLMs) excel at temporal reasoning tasks like event ordering and duration estimation, their ability to perceive the actual passage of time remains unexplored. We investigate whether LLMs perceive the passage of time and adapt their decision-making accordingly through three complementary experiments. First, we introduce the Token-Time Hypothesis, positing that LLMs can map discrete token counts to continuous wall-clock time, and validate this through a dialogue duration judgment task. Second, we demonstrate that LLMs could use this awareness to adapt their response length while maintaining accuracy when users express urgency in question answering tasks. Finally, we develop BombRush, an interactive navigation challenge that examines how LLMs modify behavior under progressive time pressure in dynamic environments. Our findings indicate that LLMs possess certain awareness of time passage, enabling them to bridge discrete linguistic tokens and continuous physical time, though this capability varies with model size and reasoning abilities. This work establishes a theoretical foundation for enhancing temporal awareness in LLMs for time-sensitive applications.