发表机构
Fudan University; Peking University; Nanyang Technological University; Tencent（复旦大学; 北京大学; 南洋理工大学; 腾讯）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出面向持久智能体的感知中心架构（Pera），用于刻画、组织和指导持久AI智能体的发展，类比软件工程的小型到大型编程，推动语言智能体向长期自适应智能系统演进。
AI 中文摘要
认知语言智能体通过为语言模型配备记忆、工具和决策程序，实现了显著进展，使智能体能够在交互式环境中进行推理和行动。现有框架大多将这些智能体视为解决用户指定的有限任务的系统。一个日益重要的目标是让语言智能体在长期环境中提供持久协助，在这种环境中，用户需求、上下文和服务流程持续存在并发生变化，且能在随时间出现的广泛任务中保持可用性。然而，我们仍然缺乏一个框架来刻画持久AI智能体、组织现有工作并指导未来发展。为此，我们提出了面向持久智能体的感知中心架构（Pera）。Pera描述了一个围绕感知和控制组件组织的持久智能体，这些组件不断从 episodic 任务执行、内部上下文和周围环境变化中感知与服务相关的信号，并利用这些信号构建生命周期任务。这些任务驱动智能体服务流程的持续运行和适应。我们使用Pera回顾性地组织近期工作，研究详细案例，并为构建更强大的持久智能体提供前瞻性见解。正如软件工程从小型编程发展到大型编程一样，Pera将语言智能体的演进视为一种类似的架构转变，朝向长期、自适应的智能系统。
英文摘要
Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded tasks. An increasingly important goal is for language agents to provide persistent assistance in long-lived settings where user needs, context, and service procedures persist and change, and to remain useful across the broad range of tasks that arise over time. Yet we still lack a framework to characterize persistent AI agents, organize existing work, and guide future development. To this end, we propose a Perception-Centered Architecture for Persistent Agents (Pera). Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks. These tasks drive the ongoing operation and adaptation of the agent's service procedures. We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent agents. Just as software engineering moved from programming in the small to programming in the large, Pera frames the evolution of language agents as an analogous architectural transition toward long-lived, adaptive intelligence systems.
Comments41 pages, 5 figures
