Self-Evolving Agents

Follow this topic Ask about this topic

Self-evolving agents are systems that use experience from task execution to change how they solve future tasks, rather than relying only on a fixed model or hand-designed workflow. Common approaches store and refine reusable skills or memories, optimize prompts and agent harnesses, train policies with reinforcement learning, or co-evolve task generators, environments, and teams of agents. These methods are tested in settings such as web and GUI use, coding, embodied robotics, scientific workflows, and reasoning benchmarks, with feedback ranging from execution outcomes to verifiers and paired validation. A central challenge is making improvements transfer to new tasks without forgetting earlier abilities or introducing unsafe behavior; reliable evaluation, update verification, and long-term monitoring remain open problems.

Latest papers

427 papers104 papers in the last four weeks, up 148% on the four weeks before. 0.6% of all new papers.

EvoTeam: Multi-Agent Collaboration via Evolving Teams
Oct 29, 2026Qinuo Cao, Xin He, Dianxuan Fu +7Multi-Agent Collaboration Multi-Agent Systems
Jilin University · Nanjing University of Science and Technology · Shanghai AI Lab
Compile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation
Oct 29, 2026Chengyu Yang, Yunxiang Zheng, Zongzheng Li +6LLM Agent Skill Learning Self-Evolving Agents
East China Normal University · China University of Geoscience
Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection
Oct 29, 2026Xinyan Wang, Xiaogeng Liu, Jun Shao +1AI Agent Security AI Agent Safety
University of Wisconsin–Madison · Johns Hopkins University
MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems
Oct 28, 2026Hehai Lin, Qi Yang, Chengwei QinMulti-Agent Orchestration Multi-Agent System Optimization
The Hong Kong University of Science and Technology (Guangzhou) · Ant Group
Evolving Agent Teams
Oct 27, 2026Shiyi Cao, Ziming Mao, Dacheng Li +2Multi-Agent Coding Self-Evolving Agents
University of California, Berkeley
Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security
Oct 26, 2026Leo Benaharon, Chi Zhang, Wei Zheng +2Robot Policy Adaptation Self-Evolving Agents
The authors are with Isuzu Technical Center of America, Plymouth, MI 48170 USA.
Hierarchical Skill Evolution for Coding Agent
Oct 26, 2026Jun Gao, Yun Peng, Changhai Zhou +10LLM Agent Skill Learning Software Engineering Agents
How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation
Oct 26, 2026Christoph Treude, Sebastian BaltesLLM Agent Harnesses Self-Evolving Agents
Singapore Management University Singapore · Heidelberg University Heidelberg, Germany
EvolveMAS: A Unified Self-Evolution Framework for Decentralized Multi-Agent Systems
Oct 25, 2026Yalun Wu, Qiwei Ma, Bingbing Xu +10Multi-Agent Systems Self-Evolving Agents
National University of Singapore · Hunan University · Institute of Computing Technology, Chinese Academy of Sciences +4
$Δτ$ -Bench: Pushing Agents Toward a Moving Capability
Oct 25, 2026Shuofei Qiao, Xuanguang Pan, Yijun Chen +6AI Agent Benchmarks LLM Agent Evaluation
Zhejiang University · University College London
Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning
Oct 25, 2026Wenzhe Fan, Benjamin Steenhoek, Gaurav Mittal +1Lifelong Learning Agents Agent Skill Learning
University of Illinois Chicago, IL, USA · Microsoft, Redmond, WA, USA
More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents
Oct 24, 2026Dianxing Shi, Dingjie Fu, Tianyu Lei +1Adaptive Reasoning in Language Models Efficient Language Model Reasoning
Beihang University · Huazhong University of Technology
CoEvolve: Counterfactual-Guided Co-Evolution of Memory and Collaboration in Multi-Agent Systems
Oct 24, 2026Xufei Shi, Derong Xu, Wei Chen +3Multi-Agent LLM Systems Multi-Agent Systems
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
Causal-based approaches to explain and learn from self-extension - A review
Oct 23, 2026Rebeca Marfil, Pablo Bustos, Antonio BanderaSelf-Evolving Agents Cognitive Architectures for AI Agents
Universidad de M´alaga, Spain · Universidad de Extremadura, Spain
RSIHub: A Composable Framework for Agent-Evolution Methods
Oct 23, 2026Zimu Wang, Xiaobo Wang, Siyu Ye +11Self-Evolving Agents LLM Agent Harnesses
University of California, Berkeley · Shanghai Jiao Tong University · University of Science and Technology of China +4
VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team
Oct 22, 2026Wenbo Hu, Ken Li, Jiazhe Wei +13AI Coding Agents Multi-Agent LLM Systems
PRLab, Nanjing University · S-Lab, Nanyang Technological University
Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity
Oct 22, 2026Ali Atiah AlzahraniMulti-Agent System Optimization Self-Evolving Agents
ADAPT for Science: A Multi-Agent System for Self-Evolving Scientific Optimization
Oct 22, 2026Zhaoran Feng, Yuchen Ni, Jianan Liu +3AI for Science Self-Evolving Agents
National Laboratory of Solid State Microstructures, School of Physics and, Collaborative Innovation Center of Advanced Microstructures,, Nanjing University, Nanjing 210093, China · Shanghai Innovation Institute, Shanghai 200231, China · College of Computer Science and Artificial Intelligence,, Fudan University, Shanghai 200433, China +2
Governed Self-Evolution for Autonomous Investing: A Multi-Agent LLM System with an Invariant Core
Oct 22, 2026Yebo Feng, Jingyang Dai, Liangrui Pan +3Self-Evolving Agents Multi-Agent LLM Systems
Nanyang Technological University Singapore, Singapore · University College London London, United Kingdom
GuideEvolve: Self-Evolving Agent Framework with Expert Guidance and 3Ts Mechanisms
Oct 21, 2026Meihong Jia, Yasemin Timar, Jonathan TawsSelf-Evolving Agents LLM Agent Self-Improvement
Amazon, Tokyo, Japan · Amazon Web Services, Luxembourg, Luxembourg
Evolving with Open Worlds: Towards Recursive Self-Improvement for Future Forecasting
Oct 21, 2026Zhipeng Chen, Yunsen Liang, Yanxi Chen +12Recursive Self-Improvement Self-Evolving Agents
Gaoling School of Artificial Intelligence, Renmin University of China · IQuest Research · Nanyang Technological University
From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation
Oct 21, 2026Tingwen Du, Haoyu Guo, Hanxue Zhang +9Robotic Manipulation Long-Horizon Robotic Manipulation
University of Science and Technology of China · Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University +2
VeriEvolve: Evaluator-First Evolution for Tool-Using Agents
Oct 21, 2026Yueshen Li, Kamer Ali Yuksel, Gokhan Tur +2Self-Evolving Agents Tool-Use Evaluation
University of Illinois Urbana-Champaign · aiXplain
Evolving Agent Interfaces
Oct 20, 2026Saaket Agashe, Yuzhe Yang, Gonzalo Gonzalez-Pumariega +5Computer-Use Agents Self-Evolving Agents
University of California, Santa Barbara · Cornell University · Language Technologies Institute, Carnegie Mellon University
Self-Evolving Agents through Privileged Retrospective Distillation
Oct 20, 2026Yuhang Zhou, Yifan Wu, Bo Peng +5Self-Evolving Agents Continual Learning for LLM Agents
Meta AI
KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses
Oct 20, 2026Zhikang Chen, Yueqing Sun, Sen Cui +6Agent Harness Optimization Long-Horizon Agent Tasks
University of Oxford · Meituan · Tsinghua University +1
EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver
Oct 19, 2026Dastin Huang, Baran Nama, Salaheddin AlzubiLLM Agent Skill Learning Self-Evolving Agents
Sentient Labs
Are Self-Evolving Agents Continual Learners?
Oct 19, 2026Xiaoyin Chen, Yizheng Huang, Yinglun Xu +4Continual Learning for LLM Agents Self-Evolving Agents
Mila – Quebec AI Institute · Université de Montréal · Work done as a student researcher at Google DeepMind +1
ACE-Trader: Adversarial Co-Evolution for Generator-Critic Trading Systems
Oct 19, 2026Chang Zhou, Jiarun Zhou, Xingtong Yu +3Algorithmic Trading Memory-Augmented Agents
University of Science and Technology of China · The Chinese University of Hong Kong
Memory as Belief: Bayesian Evolution of Memory for Self-Evolving LLM Agents
Oct 18, 2026Yiming Xu, Qian Yang, Zihan Chen +4Memory Management for LLM Agents Self-Evolving Agents
School of Computer Science and Technology, Xi’an Jiaotong University · Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering, Xi’an Jiaotong University · University of Virginia, Charlottesville, Virginia, USA +1

Oct 29, 2026J/K move · Enter open · S save

EvoTeam: Multi-Agent Collaboration via Evolving Teams

Qinuo Cao, Xin He, Dianxuan Fu, Lizhi Zhang+6

Jilin University · Nanjing University of Science and Technology · Shanghai AI Lab

Multi-Agent Collaboration Multi-Agent Systems Multi-Agent LLM Systems Multi-Agent Coordination Self-Evolving Agents

Open paper AskPDF arXiv

LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team collaboration. Recent studies have therefore extended evolution to the collaboration level, using collective execution experience to adjust team organization, and inter-agent interactions. Nevertheless, evolving collaboration across heterogeneous tasks remains challenging, as existing approaches often constrain team reorganization within a shared structure and reuse interaction rules across incompatible team contexts. In this paper, we propose EvoTeam, a collaboration-centric evolution framework that jointly evolves team organization, interaction rules, and individual agent skills through execution experience. It maintains a library of reusable teams, selecting or creating agent teams and guiding collaboration through team-specific interaction rules. Collaboration experience accumulates within compatible team contexts, while individual skills remain reusable across teams. Experiments across four benchmarks demonstrate its effectiveness. Our code is available at https://github.com/DEEP-JLU/EvoTeam.