实时时间压力下，大模型谈判策略易受干扰，反馈方式影响巨大。
Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialogues
- 用倒计时反馈替代初始期限，可显著提升谈判成功率
- 相同模型在轮次限制下接近完美闭合，说明非能力不足
- 视觉提醒比数字倒数更有效，展示方式决定效果
大型语言模型（LLMs）以离散时间逐标记生成文本，但现实沟通如心理治疗、商务谈判等高度依赖连续时间约束。我们通过模拟成对代理在严格时限下的谈判，研究其对实时压力的适应性。代理仅获知初始截止时间，或每回合收到剩余时间更新。与仅提供初始时限相比，提供剩余时间反馈使GPT-5.1-chat-latest的协议达成率从4%提升至32%，且接受率提高六倍以上。同一模型在轮次限制下接近完美闭合，表明其墙钟表现不佳并非源于谈判能力不足。在多种界面条件下，定性紧迫提示可优于数值倒数；重复提醒无法稳定复现收益；定向时间追踪对某些模型有益，对另一些则有害。在多种谈判场景与模型配置中，实时时序适应表现出脆弱性、模型依赖性和呈现方式敏感性。代码已公开于 https://github.com/sehgal-neil/llm-temporal-awareness。
原文摘要 · Abstract (English)
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. We use simulated negotiations between paired agents under strict deadlines to study adaptation to real-time pressure. Agents either receive only the initial deadline or explicit remaining-time updates at each turn. Remaining-time feedback raises deal closure from 4% to 32% for GPT-5.1-chat-latest and increases offer acceptance more than sixfold. The same model achieves near-perfect closure under turn-based limits, showing that poor wall-clock performance is not simply due to insufficient negotiation competence. Across additional interface conditions, qualitative urgency cues can outperform numeric countdowns, repeated deadline reminders do not consistently reproduce their benefits, and directed time tracking can help or hurt depending on the model. Across additional negotiation scenarios and model configurations, we find real-time temporal adaptation is fragile, model-dependent, and sensitive to how temporal constraints are presented. Code available at https://github.com/sehgal-neil/llm-temporal-awareness
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。