A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Recent advances in large language models (LLMs) have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after deployment, limiting their ability to adapt to dynamic and evolving environments. To address this limitation, recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback. This emerging direction lays the foundation for self-evolving AI agents, which bridge the static capabilities of foundation models with the continuous adaptability required by lifelong agentic systems. In this survey, we provide a comprehensive review of existing techniques for self-evolving agentic systems. Specifically, we first introduce a unified conceptual framework that abstracts the feedback loop underlying the design of self-evolving agentic systems. The framework highlights four key components: System inputs, Agent System, Environment, and Optimisers, serving as a foundation for understanding and comparing different strategies. Based on this framework, we systematically review a wide range of self-evolving techniques that target different components of the agent system, including foundation models, agent prompts, memory, tools, workflows, and communication mechanisms across agents. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where agent behaviour and optimisation objectives are tightly coupled with domain constraints. In addition, we provide a dedicated discussion on the evaluation, safety, and ethical considerations for self-evolving agentic systems, which are critical to ensuring their effectiveness and reliability. This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents, laying the foundation for the development of more adaptive, autonomous, and lifelong agentic systems.
Dynamic data sources that provide information to the agent system. Includes user queries, environmental observations, and interaction data.
The core AI agent components including foundation models, planning modules, memory systems, tools, workflows, and communication mechanisms.
The external world or specialized domain where agents operate, providing feedback and constraints that drive evolution.
Mechanisms that enable agents to self-evolve by analyzing performance, identifying deficiencies, and implementing improvements.
This repository contains a comprehensive collection of resources related to self-evolving AI agents, including: