Abstract
Self-improving autonomous agents are transitioning from research prototypes to deployed systems. The primary goal is controllable evolution or adaptation from experience with minimal or even no human input. 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.
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 the signals that drive change, then review applications and discuss evaluation, before closing with open problems and future directions.
For convenience, we track technical updates on GitHub.
Blogger's Review: The research on modern self-improving agents not only advances autonomous systems but also offers new insights into achieving more efficient artificial intelligence. By reducing human intervention, these systems can adapt more flexibly to complex environments, showcasing stronger intelligent characteristics. Future research directions are promising.