Self-Improvements in Modern Agentic Systems: A Survey

现代智能体系统的自我改进：综述

Abstract: Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input.

摘要： 具备自我改进能力的自主智能体正从研究原型转向实际部署系统。其主要目标是在极少甚至无需人工干预的情况下，通过经验实现可控的进化或适应。

This survey frames modern self-improving agents as adaptive systems that convert experience into accumulated capability gains. We offer a system-level framework that represents a modern agent as a configuration coupling a foundation model with an operational scaffold of prompts, memory, tools, and control logic.

本综述将现代自我改进型智能体定义为能够将经验转化为能力积累的自适应系统。我们提供了一个系统级的框架，将现代智能体描述为一种将基础模型与由提示词（prompts）、记忆、工具和控制逻辑构成的操作支架（operational scaffold）相结合的配置。

Within this framework, self-improvement is formalized as a self-induced update operator that obtains and commits updates to model parameters or scaffold components. We organize prior work by update target and by the signals that drive change, then review applications and discuss evaluation, before closing with open problems and future directions.

在该框架内，自我改进被形式化为一种自诱导更新算子，用于获取并提交对模型参数或支架组件的更新。我们根据更新目标和驱动变化的信号对现有研究进行了梳理，回顾了相关应用并讨论了评估方法，最后提出了尚待解决的问题及未来研究方向。

For convenience, we track technical updates on this [https URL].

为方便起见，我们在此 [URL] 链接中追踪相关的技术更新。