Can LLMs Perceive Time? An Empirical Investigation

Aniketh Garikaparthi

Keywords: Time Perception, temporal grounding, temporal self-estimation, LLM agents, agent scheduling, task completion, time horizon

TL;DR: LLMs don’t “feel” elapsed time they misestimate their own runtimes by ~4–7×, fail duration ordering, and stay miscalibrated even after finishing tasks, so scheduling must rely on external signals.

Abstract: Large language models cannot estimate how long their own tasks take. We investigate this limitation through four experiments across 68 tasks and four model families. Pre-task estimates overshoot actual duration by 4--7$\times$ ($p < 0.001$), with models predicting human-scale minutes for tasks completing in seconds. Relative ordering fares no better: on task pairs designed to expose heuristic reliance, models score at or below chance (GPT-5: 18\% on counter-intuitive pairs, $p = 0.033$), systematically failing when complexity labels mislead. Post-hoc recall is disconnected from reality---estimates diverge from actuals by an order of magnitude in either direction. These failures persist in multi-step agentic settings, with errors of 5--10$\times$. The models possess propositional knowledge about duration from training but lack experiential grounding in their own inference time, with practical implications for agent scheduling, planning and time-critical scenarios.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 112