Paper

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

Cheng, Qian, Huan-ang Gao, Wang, Mengdi, Wu, Yiran, Zhang, Jiayi, Hua, Wenyue, Ren, Qihan, Ji, Heng, Qi, Xuan, Zhao, Qiwen, Qiu, Jiahao, Liu, Hongzhang, Zhou, Yuhang, Liu, Dongrui, Zhang, Shaokun, Xinzhe Juan, Han, Xiao, Xiang, Jinyu, Hu, Minda, Hu, Mengkang, Wang, Huazheng, Wu, Qingyun, Wang, Hongru, Wang, Zhenhailong, Geng, Jiayi, Fang, Yixiong, Liu, Shilong

2026

Overview

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks but remain fundamentally static, unable to adapt their internal parameters to novel tasks, evolving knowledge domains, or dynamic interaction contexts. As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck, necessitating agents that can adaptively reason, act, and evolve in real time. This paradigm shift -- from scaling static models to developing self-evolving agents -- has sparked growing interest in architectures and methods enabling continual learning and adaptation from data, interactions, and experiences. This survey provides the first systematic and comprehensive review of self-evolving agents, organizing the field around three foundational dimensions: what, when, and how to evolve. We examine evolutionary mechanisms across agent components (e.g., models, memory, tools, architecture), categorize adaptation methods by stages (e.g., intra-test-time, inter-test-time), and analyze the algorithmic and architectural designs that guide evolutionary adaptation (e.g., scalar rewards, textual feedback, single-agent and multi-agent systems). Additionally, we analyze evaluation metrics and benchmarks tailored for self-evolving agents, highlight applications in domains such as coding, education, and healthcare, and identify critical challenges and research directions in safety, scalability, and co-evolutionary dynamics. By providing a structured framework for understanding and designing self-evolving agents, this survey establishes a roadmap for advancing more adaptive, robust, and versatile agentic systems in both research and real-world deployments, and ultimately sheds light on the realization of Artificial Super Intelligence (ASI) where agents evolve autonomously and perform beyond human-level intelligence across tasks.

• Publisher: Cornell University Library, arXiv.org
• Subject: Adaptation / Evolution / Human performance / Intelligence / Large language models / Multiagent systems / Static models / Testing time