arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.04898cs.AI
收藏

演化环境中的实时推理智能体

Real-Time Reasoning Agents in Evolving Environments

Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);Georgia Institute of Technology(佐治亚理工学院);Stanford University(斯坦福大学)

Yule Wen, Yixin Ye, Yanzhe Zhang, Diyi Yang, Hao Zhu

AI总结:

本文提出实时推理问题与Real-Time Reasoning Gym环境,并设计同时结合反应式与规划式推理的AgileThinker,在动态高时间压力任务中优于单一范式智能体。

摘要:

现实世界中的智能体不仅必须做出合乎逻辑的判断,还必须做出及时的判断。这要求智能体持续感知动态环境:危险出现、机会产生、其他智能体采取行动,而智能体自身的推理仍在进行中。尽管语言模型推理取得了进展,现有方法未能考虑这种动态特性。我们将实时推理作为演化环境中智能体的一个新问题表述引入,并构建了 Real-Time Reasoning Gym 来展示该问题。我们研究了在智能体中部署语言模型的两种范式:(1)反应式智能体,采用具有有界推理计算的语言模型以实现快速响应;(2)规划式智能体,允许扩展推理计算以处理复杂问题。我们的实验表明,即使是最先进的模型,在任一范式下也难以做出合乎逻辑且及时的判断。为了解决这一局限,我们提出了 AgileThinker,它同时启用两种推理范式。随着任务难度和时间压力的上升,AgileThinker 始终优于仅采用单一推理范式的智能体,有效地平衡了推理深度与响应延迟。我们的工作将实时推理确立为开发实用智能体的关键测试平台,并为时间受限的人工智能系统研究提供了基础,指明了一条通往具备实时能力的智能体的路径。

英文摘要:

Agents in the real world must make not only logical but also timely judgments. This requires continuous awareness of the dynamic environment: hazards emerge, opportunities arise, and other agents act, while the agent's reasoning is still unfolding. Despite advances in language model reasoning, existing approaches fail to account for this dynamic nature. We introduce real-time reasoning as a new problem formulation for agents in evolving environments and build Real-Time Reasoning Gym to demonstrate it. We study two paradigms for deploying language models in agents: (1) reactive agents, which employ language models with bounded reasoning computation for rapid responses, and (2) planning agents, which allow extended reasoning computation for complex problems. Our experiments show that even state-of-the-art models struggle with making logical and timely judgments in either paradigm. To address this limitation, we propose AgileThinker, which simultaneously engages both reasoning paradigms. AgileThinker consistently outperforms agents engaging only one reasoning paradigm as the task difficulty and time pressure rise, effectively balancing reasoning depth and response latency. Our work establishes real-time reasoning as a critical testbed for developing practical agents and provides a foundation for research in temporally constrained AI systems, highlighting a path toward real-time capable agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑