跳到正文
arXiv cs.AI· Hongguan Su, Ming Wang, Shun Zhang, Yifan Wang, Rong Yin, Zhiming Ma, Mengzheng Yang, Peng Chen·· 4 小时前AI 评分50

arXiv 论文检验长程智能体在对话中断后的时间感知与适应能力

Can Agents Keep Up with Time? An Empirical Analysis of Temporal Adaptation After a Conversational Hiatus

AI 导读

arXiv 论文(arXiv:2611.17806)研究长程智能体的时间状态感知与使用能力,设计 session-rekindling 任务,固定此前对话、只变化后续日期和时间信息传递方式。

正文 · 原文

View PDF HTML (experimental)

Abstract:Long-horizon agents increasingly serve as persistent personal assistants across modern web platforms, managing schedules, applications, and multi-step plans over weeks or months. Users often return to an ongoing conversation after a long conversational hiatus, while earlier bookings and preparation notes stay on record. During this hiatus, scheduled dates may pass even though the retained records remain unchanged and event outcomes go unrecorded. Existing evaluations of long-horizon agents focus on fact retention and explicit state updates. Whether agents perceive the passage of time and adapt their advice accordingly therefore remains unknown. We frame this ability as temporal state perception and use, which means perceiving the current time and applying it when interpreting dated records. To study it, we design session-rekindling tasks that keep the earlier conversation fixed and vary only the follow-up date and the way temporal information reaches the agent. Experiments across five model routes and five temporal-information conditions show that agents can obtain the current time but often fail to use it. They reliably query the clock and even note in their reasoning that the scheduled date has passed, yet many still tell users to prepare for the expired event. Supplying explicit temporal context reduces this error, and providing the computed date relation removes it entirely. Keeping up with time therefore depends on turning perceived time into updated plans. Based on these findings, we design a session-rekindling benchmark that provides temporal-awareness guidance for designing long-horizon agents. The code can be found at this https URL.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.17806 [cs.AI]
  (or arXiv:2611.17806v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.17806

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hongguan Su [view email]
[v1] Fri, 13 Nov 2026 06:42:03 UTC (6,657 KB)

来源:arXiv cs.AI · arxiv.org