大规模智能体：面向持久化智能体的以感知为中心的架构

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，使其能够在交互环境中进行推理和行动，从而取得了显著进展。现有框架在很大程度上将这些智能体视作求解用户指定的、有界任务的系统。一个日益重要的目标是：让语言智能体在用户需求、上下文和服务流程持续存在且不断变化的长期环境中提供持续性协助，并能在随时间涌现的各类任务中持续发挥作用。然而，我们仍然缺乏一种能够刻画持续型AI智能体、梳理现有工作并指导未来发展的框架。为此，我们提出了一种面向持续智能体的以感知为中心的架构（Perception-Centered Architecture for Persistent Agents, Pera）。Pera 将持久智能体描述为围绕感知组件与控制组件组织起来的系统：这些组件持续感知来自情节性任务执行、内部上下文以及周围环境变化中与服务相关的信号，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与适应。我们使用 Pera 对近期工作进行回顾性梳理，考察一个详细的案例研究，并为构建能力更强的持久智能体提供前瞻性洞见。正如软件工程从“小型编程”走向“大型编程”一样，Pera 也将语言智能体的演化框定为一种类似的架构转型，即朝向长期运行的自适应智能系统。

English

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.