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.

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
May 26, 2026Yuchen Guo, Junli Gong, Weicheng Wang +3Continual Learning for LLM Agents LLM Agent Memory
Northwestern University · Northeastern University · South China University of Technology +2
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
May 26, 2026Huawei Lin, Peng Li, Jie Song +2LLM Agent Skill Learning LLM Agent Skill Retrieval
ByteDance Inc.
Governed Evolution of Agent Runtimes through Executable Operational Cognition
May 26, 2026Mariano Garralda-BarrioMulti-Agent Orchestration AI Agent Governance
Independent Researcher Lleida, Spain
Darwin Mobile Agent: A Roadmap for Self-Evolution
May 26, 2026Daniel Beechey, Derek Yuen, Jianheng Liu +5Reinforcement Learning RL for GUI Agents
1Huawei Noah’s Ark Lab · University College London
Constitutional Arms Races in the Public Goods Game: Co-Evolving LLM Constitutions Under Cooperation-Defection Pressure
May 26, 2026Ujwal Kumar, Arth Singh, Hershraj Niranjani +5LLM Red Teaming Multi-Agent LLMs
Shibaura Institute of Technology · NIT Agartala · UC Berkeley +2
CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly
May 25, 2026Yihe Fan, Changyi Li, Lichen Xu +4LLM Agent Self-Improvement Automated Penetration Testing
Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Shanghai Pudong Research Institute of Cryptology
When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills
May 25, 2026Yunfei Wang, Xiaohao Xu, Yang Li +1Robotics LLM Agent Skill Learning
University of Michigan, Ann Arbor
CODESKILL: Learning Self-Evolving Skills for Coding Agents
May 25, 2026Yanzhou Li, Yiran Zhang, Xiaoyu Zhang +2Coding Agents LLM Agent Skill Learning
Nanyang Technological University · 2Zhejiang University
PACE: Two-Timescale Self-Evolution for Small Language Model Agents
May 21, 2026Chen Ling, Pei Chen, Albert Guan +4Small Language Models LLM Agent Workflow Optimization
Amazon
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
May 21, 2026Qianshu Cai, Yonggang Zhang, Xianzhang Jia +5Software Engineering Agents LLM Agent Self-Improvement
University of Science and Technology of China · Hong Kong Generative AI Research & Development Center · The Hong Kong University of Science and Technology +1
EVE-Agent: Evidence-Verifiable Self-Evolving Agents
May 21, 2026Yamato Arai, Yuma IchikawaLLM Agent Self-Improvement LLM Agent Training
Fujitsu Limited Department of Basic Science · The University of Tokyo · Fujitsu Limited +1
Self-Evolving Multi-Agent Systems via Decentralized Memory
May 21, 2026Guangya Hao, Yunbo Long, Zhuokai ZhaoMulti-Agent LLM Systems LLM Agent Memory
University of Cambridge · University of Chicago
Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
May 21, 2026Chengcheng Wang, Qinhua Xie, Wei He +3Scientific Workflow Automation Autonomous Experimentation
University of Sydney · 2East China Normal University · 3TokenRhythm AI +1
Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents
May 21, 2026Xing Zhang, Yanwei Cui, Guanghui Wang +4Continual Learning for LLM Agents LLM Agent Self-Improvement
AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China
FlyRoute: Self-Evolving Agent Profiling via Data Flywheel for Adaptive Task Routing
May 21, 2026Rongjun Li, Ziyu Zhou, Yihang WuAdaptive Model Routing Self-Evolving Agents
IT Innovation and Research Center, Huawei Technologies · h-partners
Dynamic Mixture of Latent Memories for Self-Evolving Agents
May 21, 2026Dianzhi Yu, Vireo Zhang, Hongru Wang +7Continual Learning for LLMs Mixture-of-Experts Language Models
The Chinese University of Hong Kong · Nanyang Technological University · University of Edinburgh +2
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
May 20, 2026Sixiang Chen, Zhaohu Xing, Tian Ye +7Agentic Image Generation LLM Agent Self-Improvement
The Hong Kong University of Science and Technology (Guangzhou) · Meituan · The Hong Kong University of Science and Technology +1
APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
May 20, 2026Yibo Li, Jiashuo Yang, Zhi Zheng +5LLM Agents Long-Horizon LLM Agents
1National University of Singapore · 2Beijing University of Posts and Telecommunications
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
May 19, 2026Xing Zhang, Yanwei Cui, Guanghui Wang +4Continual Learning for LLM Agents LLM Agent Self-Improvement
1AWS Generative AI Innovation Center · 2HSBC Holdings Plc., HSBC Technology Center, China.
Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
May 18, 2026Nga Teng Chan, Yi Zhang, Yechi Liu +9Embodied Navigation World Model-Based Planning
1The Hong Kong University of Science and Technology · 2X-Humanoid · Institute of Automation, CAS +1
EXG: Self-Evolving Agents with Experience Graphs
May 18, 2026Yuxin Jin, Siyuan Zhang, Hanchen Wang +3Graph-Based Agent Memory Memory-Augmented Agents
University of Technology Sydney Sydney, Australia · The University of New South Wales Sydney, Australia
Taming "Zombie'' Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution
May 17, 2026Taolin Zhang, Pukun Zhao, Qizhou Chen +5Multi-Agent LLM Systems Multi-Agent Coordination
School of Computer Science and Information Engineering, Hefei University of Technology · Guangdong University of Finance and Economics · East China Normal University +1
SE-GA: Memory-Augmented Self-Evolution for GUI Agents
May 16, 2026Shilong Jin, Lanjun Wang, Zhuosheng ZhangGUI Agents Mobile GUI Agents
College of Intelligence and Computing, Tianjin University, Tianjin, China · School of New Media and Communication, Tianjin University, Tianjin, China · School of Computer Science, Shanghai Jiao Tong University, Shanghai, China
FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast
May 15, 2026Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3LLM Agent Memory LLM Agent Self-Improvement
Carleton University Ottawa, Ontario, Canada · Defence R&D Canada Ottawa, Ontario, Canada · Cistel Technology Ottawa, Ontario, Canada
TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices
May 15, 2026Junle Wang, Xingchuang Liao, Wenjun WuSoftware Engineering Multi-Agent Orchestration
School of Artificial Intelligence, Beihang University Beijing, China
DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
May 14, 2026Yikun Zhang, Xiwei Cheng, Tianyu Liu +2AI Agents for Scientific Discovery AI-Assisted Scientific Research
1Northeastern University · 2Broad Institute of MIT and Harvard · 3Yale University +1
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
May 14, 2026Shihao Qi, Jie Ma, Rui Xing +15Multi-Agent Collaboration LLM Agent Self-Improvement
MOE KLINNS Lab · School of Cyber Science and Engineering, Xi’an Jiaotong University · School of Software Engineering, Xi’an Jiaotong University +6
Harnessing Agentic Evolution
May 13, 2026Jiayi Zhang, Yongfeng Gu, Jianhao Ruan +10Evolutionary Optimization Self-Improving Agents
1The Hong Kong University of Science and Technology (Guangzhou) · 2DeepWisdom · 3Singapore University of Technology and Design +4
EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
May 13, 2026Jiaqi Liu, Xinyu Ye, Peng Xia +4LLM Agent Memory LLM Memory
UNC-Chapel Hill · UC Berkeley · UCSC
Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems
May 12, 2026Zhaojiacheng ZhouLLM Agent Security Automated Red Teaming
Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai 200240, China

May 26, 2026J/K move · Enter open · S save

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

Yuchen Guo, Junli Gong, Weicheng Wang, Hongmin Cai+2

Northwestern University · Northeastern University · South China University of Technology+2

Continual Learning for LLM Agents LLM Agent Memory Self-Evolving Agents Memory-Augmented Language Model Agents Long-Term Memory for Embodied Agents

Open paper AskPDF arXiv

We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience. PEAM pairs a slow deliberative LLM for open-ended reasoning with a fast parametric module for reflexive execution of consolidated skills. The fast module is a multimodal Mixture-of-Experts LoRA architecture with per-category physically isolated adapters, enabling parameter-level continual learning without catastrophic forgetting. We treat failure as a first-class training signal: failure--correction trajectory pairs are internalized through a joint behavioral-cloning and contrastive objective, so the agent learns not only what succeeds but also how corrected actions differ from failed ones. To govern consolidation, PEAM introduces a parameterization-worthiness score for deciding which experience should be internalized, and a scale-free self-triggered consolidation mechanism for deciding when to internalize without task-specific hand-tuned thresholds, making the agent self-evolving as the trigger transfers across task distributions without re-tuning. Experiments in Minecraft show that PEAM improves long-horizon task performance, mitigates forgetting on previously consolidated skills, and improves parametric-versus-retrieval efficiency over retrieval-based embodied agents and parametric memory variants.