arxiv:2508.07407

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Published on Aug 10

· Submitted by

X-iZhang on Aug 12

#3 Paper of the day

Upvote

Authors:

Jinyuan Fang ,

Xi Zhang ,

Yingxu Wang ,

Xi Wang ,

Zaiqiao Meng

Abstract

A survey of self-evolving AI agents that adapt to dynamic environments through automatic enhancement based on interaction data and feedback.

AI-generated summary

Recent advances in large language models 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 this end, 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. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where 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.

View arXiv page View PDF Project page GitHub 104 Add to collection

Community

X-iZhang

Paper author Paper submitter 4 days ago

This survey provides a comprehensive overview of the emerging field of Self-Evolving AI Agents, highlighting key development trends and technological shifts.

We define this new paradigm — Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems.

Definition: Self-evolving AI agents are autonomous systems that continuously and systematically optimise their internal components through interaction with environments, with the goal of adapting to changing tasks, contexts and resources while preserving safety and enhancing performance.

Meanwhile, we propose a set of guiding principles for safe and effective self-evolution of AI agents. Specifically, we articulate the Three Laws of Self-Evolving AI Agents (inspired by Asimov’s Three Laws of Robotics):

Endure (Safety Adaptation):
Self-evolving AI agents must maintain safety and stability during any modification;
Excel (Performance Preservation):
Subject to the First law, self-evolving AI agents must preserve or enhance existing task performance;
Evolve (Autonomous Evolution):
Subject to the First and Second law, self-evolving AI agents must be able to autonomously optimise their internal components in response to changing tasks, environments, or resources.

This survey proposes a unified conceptual framework for self-evolving agents, consisting of four core components — System Inputs, Agent System, Environment, and Optimisers. It systematically reviews evolution strategies across foundation models, prompts, memory, tools, workflows, and inter-agent communication, and examines domain-specific adaptations in biomedicine, programming, and finance. We further discuss key challenges in evaluation, safety, and ethics, laying the groundwork for the next generation of adaptive, autonomous, and lifelong agentic systems.