Real-Time Deadlines Reveal Temporal Awareness Failures in LLM Strategic Dialogues

TL;DR

This paper investigates how large language models struggle with real-time temporal awareness during negotiations, revealing a significant gap in their ability to track elapsed time under deadlines, which impacts their performance in time-sensitive tasks.

Contribution

The study demonstrates that LLMs fail to internally track elapsed time in real-time settings, highlighting a critical limitation in their deployment for time-sensitive applications.

Findings

Deal closure rates increase with time-awareness cues

LLMs perform well under turn-based time limits

Temporal tracking failure is consistent across models and scenarios

Abstract

Large Language Models (LLMs) generate text token-by-token in discrete time, yet real-world communication, from therapy sessions to business negotiations, critically depends on continuous time constraints. Current LLM architectures and evaluation protocols rarely test for temporal awareness under real-time deadlines. We use simulated negotiations between paired agents under strict deadlines to investigate how LLMs adjust their behavior in time-sensitive settings. In a control condition, agents know only the global time limit. In a time-aware condition, they receive remaining-time updates at each turn. Deal closure rates are substantially higher (32\% vs. 4\% for GPT-5.1) and offer acceptances are sixfold higher in the time-aware condition than in the control, suggesting LLMs struggle to internally track elapsed time. However, the same LLMs achieve near-perfect deal closure rates ($\geq$95\%) under turn-based limits, revealing the failure is in temporal tracking rather than strategic reasoning. These effects replicate across negotiation scenarios and models, illustrating a systematic lack of LLM time awareness that will constrain LLM deployment in many time-sensitive applications.