Lifelong Learning Agents

Follow this topic Ask about this topic

Lifelong learning agents study how AI systems can keep adapting through ongoing interaction instead of relying only on a fixed training phase. Common approaches include persistent memory and selective retrieval, extracting and composing reusable skills, online reinforcement learning, and updating or combining policies as tasks change. Researchers evaluate these methods in long-horizon settings such as embodied navigation, simulated worlds, web tasks, and multi-session conversations, where agents must both improve and retain earlier capabilities. A central challenge is deciding what experience to preserve and when to reuse it: helpful transfer can also cause forgetting, interference, or reliance on outdated information.

Latest papers

52 papers11 papers in the last four weeks, up 175% on the four weeks before. 0.1% of all new papers.

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
Phronix: The Capability-Centric Learning Paradigm for Agents
Oct 22, 2026Hariharan Devarajan, Neeraj Rajesh, Aniruddha Marathe +3LLM Agent Skill Learning LLM Agent Harnesses
Lawrence Livermore National Laboratory · Illinois Institute of Technology · University of Tennessee, Knoxville
Memory-Centric Continual Learning for AI Agents
Oct 21, 2026Dongfang Li, Zhuoen Chen, Bonian Jia +25Memory-Augmented Agents Lifelong Learning Agents
Learning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents
Oct 19, 2026Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang +1Memory Management for LLM Agents Lifelong Learning Agents
School of Artificial Intelligence, Nanjing University · National Key Laboratory for Novel Software Technology, Nanjing University
Selm: Self-Evolving Library Management for Multi-Skill Agent Optimization
Oct 17, 2026Mengxi Hu, Yuxuan Hu, Jinbo Su +6LLM Agent Skill Learning LLM Agents
School of Information, Renmin University of China, Beijing, China · Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China · Beijing Academy of Artificial Intelligence, Beijing, China +2
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory
Oct 14, 2026Minghao Guo, Qingyue Jiao, Xiujin Liu +77Multimodal Memory Memory-Augmented Agents
AgentGarten: Code Worlds for Evolving Agents
Oct 8, 2026Jiawei Chi, Shangchen Miao, Zhiyuan Shi +12Self-Evolving Agents Neural Rendering
MirroS Lab
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
Oct 2, 2026Saptarshi Nath, Inish M. D'Souza, Antonio Carta +2Continual RL Lifelong Learning Agents
Department of Computer Science Loughborough University · Department of Computer Science University of Pisa · Department of Computer Science
Learning from Research: Toward Lifelong Agent Harness Evolution
Sep 30, 2026Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3Large Language Model-Guided Optimization Lifelong Learning Agents
University of California, Santa Barbara · Microsoft
ASENA: Self-evolving Agents for Embodied Navigation
Sep 30, 2026An-Chieh Cheng, Isabella Liu, Edmund Bu +7Embodied Navigation Large Language Model-Based Robot Planning
NVIDIA · University of California, San Diego
STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games
Sep 30, 2026Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang +4Multi-Agent Coordination Game-Playing Agents
School of Instrumentation Science and Optoelectronic Engineering, Beijing University of Aeronautics and Astronautics · Tsinghua University · University of Chinese Academy of Sciences +2
CORTEX: A Verified Experience Layer for Generalist Agents
Sep 27, 2026Garapati Keerthana, Manik GuptaAI Agent Reliability Lifelong Learning Agents
Birla Institute of Technology and Science, Pilani, Hyderabad, India
ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
Sep 15, 2026Cai Ke, Xin Liu, Han Zhang +6Test-Time Adaptation Lifelong Learning Agents
Pengcheng Laboratory, China · Harbin Institute of Technology, Shenzhen, China · China Unicom Greater Bay Area Innovation Institute, China
Homeostatic Continual Learning
Sep 12, 2026Yue JinContinual Learning Lifelong Learning Agents
Nokia Bell Labs France
Agents in the Large: Perception-Centered Architecture for Persistent Agents
Aug 31, 2026Shihan Dou, Haoxiang Jia, Shichun Liu +14Cognitive Architectures for AI Agents Lifelong Learning Agents
NLP Lab, Fudan University · PL Lab, Peking University · CCDS, Nanyang Technological University +1
Towards Reversible Forgetting: Managing Obsolete Knowledge in Continual Enterprise AI Agents
Aug 18, 2026Nilutpaul Sarker Yash, Tirtho Roy, Ushashi BhattacharjeeAgent Memory Management Continual Learning
TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments
Aug 14, 2026Qingren Yao, Yaxuan Kong, Yuqi Nie +6Agentic Time Series Forecasting Time Series QA
Eindhoven University of Technology · University of Oxford · VulpiVox Intelligence +2
Quo Vadis, World Modeling?
Aug 3, 2026Yu Yang, Xuemeng Yang, Licheng Wen +17World Model Learning Lifelong Learning Agents
PATH-Bench: Path-Dependent Evaluation of Lifelong Agents
Aug 2, 2026Xidong Yang, Xingyi Zhang, Wenhao Li +7Continual Learning for LLM Agents Lifelong Learning Agents
East China Normal University · Tongji University · Ant Group +5
PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
Jul 5, 2026Sukanta GangulyLLM Serving LLM Agent Memory
NetApp
Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments
Jul 1, 2026Jinwoo Jang, Daniel J. Rho, Sihyung Yoon +2World Model Learning World Models
Sungkyunkwan University · Corresponding author
AhaBench: Do Agents Turn Experience into Reusable Insights? A Long-Horizon Benchmark for Continual Learning
Jun 30, 2026Zerui Cheng, Jiawei Xu, Huacan Chai +3Continual Learning for LLM Agents Lifelong Learning Agents
Princeton University · Tencent Hy · Tsinghua University +2
Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention
Jun 24, 2026Luke McDermott, Robert W. Heath, Rahul ParhiLifelong Learning Agents Long-Context Modeling
UC San Diego
Social World Model for Lifelong Social Intelligence
Jun 19, 2026Yu LuoContinual Learning for LLM Agents Lifelong Learning Agents
Central South University
LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure
Jun 13, 2026Daksh Mittal, Tommaso Castellani, Thomson Yen +7Continual Learning for LLM Agents Lifelong Learning Agents
1Columbia University · 2Oumi
AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning
Jun 9, 2026Hang Yin, Yinan Liang, Jiazhao Zhang +4RL for Robotics Continual Robot Learning
Tsinghua University, Beijing 100084, China · Galbot Robotics, Beijing, China · Peking University, Beijing 100871, China +1
An Information-Theoretic Definition for Open-Ended Learning
Jun 6, 2026Wanqiao Xu, Yifan Zhu, Benjamin Van RoyLifelong Learning Agents RL Exploration
Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents
Jun 3, 2026Bo Mao, Jie Zhou, Yutao Yang +5Lifelong Learning Agents LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University · Shanghai AI Laboratory · Software Engineering Institute, East China Normal University
Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers
Jun 3, 2026Edward Y. ChangLifelong Learning Agents Causal Structure Learning
Computer Science Stanford University
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
Jun 2, 2026Yuan Xiong, Ziqi Miao, Qian Chen +6Lifelong Learning Agents LLM Agent Skill Learning
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China +1

Oct 25, 2026J/K move · Enter open · S save

Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning

Wenzhe Fan, Benjamin Steenhoek, Gaurav Mittal, Yu Hu

University of Illinois Chicago, IL, USA · Microsoft, Redmond, WA, USA

Lifelong Learning Agents Agent Skill Learning Self-Evolving Agents

Open paper AskPDF arXiv

Autonomous agents are increasingly deployed across sequences of related tasks, yet they often fail to retain and improve their knowledge over time. Existing approaches convert interaction trajectories into memories or reusable skills, but experience is not automatically reliable knowledge. Automatically collected skills and memories can propagate errors, mislead, and corrupt useful knowledge. To address this gap, we introduce Knowledge Evolution from Expertise and Lessons (KEEL), an agent-agnostic framework that uses verifier evidence to transform successful behavior into reusable skills and failures into corrective lessons. As new evidence accumulates, individual skill claims can be supported, contradicted, replaced, or retired. On SkillFlow benchmark, KEEL improves task success by 4.2 to 21.7 percentage points over the no-knowledge baseline, compared with gains of 2.4 to 9.6 points from SkillFlow's default method. Ablations show that skills and lessons are complementary. These results show that reliable continual agent learning depends not simply on accumulating experience, but on continually validating and evolving the knowledge derived from it. Our code is available at: https://github.com/microsoft/KEEL-TTCL26.