# Can LLMs Perceive Time? An Empirical Investigation

arXiv: https://arxiv.org/abs/2604.00010 · HTML: https://mlsanity.com/paper/2604.00010/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 30 of 40)

- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [Measuring AI Ability to Complete Long Software Tasks](https://mlsanity.com/paper/2503.14499/) (2025)
- [MMVU: Measuring Expert-Level Multi-Discipline Video Understanding](https://mlsanity.com/paper/2501.12380/) (2025)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [What Matters in Building Vision-Language-Action Models for Generalist Robots](https://mlsanity.com/paper/2412.14058/) (2024)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning](https://mlsanity.com/paper/2503.11495/) (2025)
- [Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning](https://mlsanity.com/paper/2005.07064/) (2020)
- [AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks](https://mlsanity.com/paper/2602.16901/) (2026)
- [Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark](https://mlsanity.com/paper/2504.14693/) (2025)
- [AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration](https://mlsanity.com/paper/2602.03786/) (2026)
- [Embodied AI: From LLMs to World Models](https://mlsanity.com/paper/2509.20021/) (2025)
- [Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents](https://mlsanity.com/paper/2509.03581/) (2025)
- [Time Blindness: Why Video-Language Models Can't See What Humans Can?](https://mlsanity.com/paper/2505.24867/) (2025)
- [Do Language Models Understand Time?](https://mlsanity.com/paper/2412.13845/) (2024)
- [Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time](https://mlsanity.com/paper/2409.13338/) (2024)
- [How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs](https://mlsanity.com/paper/2507.08960/) (2025)
- [Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception](https://mlsanity.com/paper/2510.23853/) (2025)

## Built on by (most cited first, 3 of 3)

- [SentinelBench: A Benchmark for Long-Running Monitoring Agents](https://mlsanity.com/paper/2606.05342/) (2026)
- [Temporal Preference Concepts and their Functions in a Large Language Model](https://mlsanity.com/paper/2606.05194/) (2026)
- [AgentTime: Can Agents Estimate and Control Their Own Runtime?](https://mlsanity.com/paper/2610.09944/) (2026)

## Abstract (arXiv)

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× (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×. 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.