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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sehgal, Neil K. R., Guntuku, Sharath Chandra, Ungar, Lyle
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911386432438272
author Sehgal, Neil K. R.
Guntuku, Sharath Chandra
Ungar, Lyle
author_facet Sehgal, Neil K. R.
Guntuku, Sharath Chandra
Ungar, Lyle
contents 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$95\%) under turn-based limits, revealing the failure is in temporal tracking rather than strategic reasoning. These effects replicate across negotiation scenarios and models, illustrating a systematic lack of LLM time awareness that will constrain LLM deployment in many time-sensitive applications.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13206
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Real-Time Deadlines Reveal Temporal Awareness Failures in LLM Strategic Dialogues
Sehgal, Neil K. R.
Guntuku, Sharath Chandra
Ungar, Lyle
Artificial Intelligence
Large Language Models (LLMs) generate text token-by-token in discrete time, yet real-world communication, from therapy sessions to business negotiations, critically depends on continuous time constraints. Current LLM architectures and evaluation protocols rarely test for temporal awareness under real-time deadlines. We use simulated negotiations between paired agents under strict deadlines to investigate how LLMs adjust their behavior in time-sensitive settings. In a control condition, agents know only the global time limit. In a time-aware condition, they receive remaining-time updates at each turn. Deal closure rates are substantially higher (32\% vs. 4\% for GPT-5.1) and offer acceptances are sixfold higher in the time-aware condition than in the control, suggesting LLMs struggle to internally track elapsed time. However, the same LLMs achieve near-perfect deal closure rates ($\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.
title Real-Time Deadlines Reveal Temporal Awareness Failures in LLM Strategic Dialogues
topic Artificial Intelligence
url https://arxiv.org/abs/2601.13206