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

2026-01-19

AI Summary

This study addresses the limited awareness of continuous temporal constraints in large language models (LLMs) during real-time dialogue, which hinders their ability to dynamically adjust strategies under genuine time limits. By designing a multi-agent negotiation task with strict deadlines, the work systematically compares model performance when provided with remaining time versus only total time allowance, revealing for the first time that strategic failures stem from deficient time tracking rather than inadequate reasoning capacity. The authors propose a reproducible evaluation framework integrating real-time temporal prompts and controlled experiments, validated across multiple mainstream LLMs. Results demonstrate that incorporating explicit time awareness substantially improves agreement rates—e.g., increasing from 4% to 32% for GPT-5.1—and exceeds 95% under turn-based constraints, confirming that LLMs possess latent strategic capabilities but lack intrinsic temporal awareness.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• temporal awareness
• real-time deadlines
• large language models
• time-sensitive communication
• strategic dialogues

Innovation

• temporal awareness
• real-time deadlines
• LLM strategic dialogue
• time-sensitive negotiation
• elapsed time tracking