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experience to preserve and when to reuse it: helpful transfer can also cause forgetting, interference, or reliance on outdated information.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.

Position: Deployed Reinforcement Learning should be Continual
Jun 1, 2026Parnian Behdin, Kevin Roice, Golnaz MesbahiNon-Stationary RL Reinforcement Learning
Alberta Machine Intelligence Institute (Amii), Edmonton, Canada.
MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains
May 28, 2026Ashutosh Ojha, Vinay Aggarwal, Ashutosh Srivastava +3Lifelong Learning Agents Agent Skill Learning
Adobe, Media & Data Science Research Lab
Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
Apr 22, 2026Yuxuan Cai, Wei Li, Jie Zhou +4Lifelong Learning Agents LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University, Shanghai · Shanghai AI Laboratory
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Apr 20, 2026Guanting Dong, Junting Lu, Junjie Huang +17Lifelong Learning Agents AI Agent Benchmarks
Renmin University of China · ByteDance Seed
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
Apr 19, 2026Ziao Zhang, Kou Shi, Shiting Huang +13Lifelong Learning Agents Long-Horizon Agent Evaluation
University of Science and Technology of China · University of Toronto · University of Sydney
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
Apr 16, 2026Lute Lillo, Nick CheneyNon-Stationary RL Reinforcement Learning
Department of Computer Science, University of Vermont, USA
LIFE -- an energy efficient advanced continual learning agentic AI framework for frontier systems
Apr 14, 2026Anne Lee, Gurudutt HosangadiLifelong Learning Agents Energy-Efficient ML
AI Research Lab, Nokia Bell Labs, Naperville, USA · AI Research Lab, Nokia Bell Labs, Murray Hill, USA
OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation
Apr 14, 2026Jiahua Pei, Yi Liu, Guoping Pan +3Object-Goal Navigation Open-Vocabulary Object Navigation
Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
Apr 1, 2026Jiaqi Liu, Zipeng Ling, Shi Qiu +9Agent Memory Multimodal Memory
UNC-Chapel Hill · University of Pennsylvania · University of California, Santa Cruz +2
PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor
Apr 1, 2026Yutao Yang, Junsong Li, Qianjun Pan +7Lifelong Learning Agents Agent Skill Learning
School of Computer Science and Technology, East China Normal University · Shanghai AI Laboratory · School of Psychology and Cognitive Science, East China Normal University
Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web
Mar 30, 2026Xiaohang Nie, Zihan Guo, Kezhuo Yang +9Web Agents LLM Agent Harnesses
Shanghai Innovation Institute · Harbin Institute of Technology · Holos Engineering +3
COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game
Mar 30, 2026Alkis Sygkounas, Rishi Hazra, Andreas Persson +2Lifelong Learning Agents Self-Evolving Agents
Machine Perception and Interaction Lab, Örebro University, Sweden
Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems
Mar 27, 2026Shanglin Wu, Yuyang Luo, Yueqing Liang +4Multi-Agent LLM Systems Multi-Agent Systems
Emory University · Illinois Institute of Technology · University of Notre Dame +1
ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents
Mar 25, 2026Bingqing Wei, Zhongyu Xia, Dingai Liu +3Lifelong Learning Agents VLMs for Robotics
Wangxuan Institute of Computer Technology, Peking University, Beijing, China
Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
Mar 16, 2026Emmanuel Dupoux, Yann LeCun, Jitendra MalikCognitive Architectures for AI Agents Lifelong Learning Agents
FAIR at META · École des Hautes Études en Sciences Sociales · NYU +1
Universe Routing: Why Self-Evolving Agents Need Epistemic Control
Mar 16, 2026Zhaohui Geoffrey WangSelf-Evolving Agents Lifelong Learning Agents
USC Viterbi School of Engineering University of Southern California Los Angeles, CA 90089, USA
Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces
Mar 15, 2026Jiayuan Du, Yuebing Song, Yiming Zhao +6Dirichlet Process Mixture Models End-to-End Autonomous Driving
Tongji University, Shanghai, China
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Mar 1, 2026Yutao Yang, Junsong Li, Qianjun Pan +9LLM Agent Skill Learning Lifelong Learning Agents
School of Computer Science and Technology, East China Normal University · Shanghai AI Laboratory
Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
Feb 26, 2026Max S. Bennett, Thomas P. Zollo, Richard ZemelMemory-Augmented Neural Networks Lifelong Learning Agents
Columbia University
Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning
Feb 23, 2026Nathan Gavenski, Felipe Meneguzzi, Odinaldo RodriguesImitation Learning Agent Skill Learning
King’s College London, London, United Kingdom · University of Aberdeen & PUCRS, Aberdeen, United Kingdom
Representation Stability in a Minimal Continual Learning Agent
Feb 23, 2026Vishnu SubramanianContinual Learning Lifelong Learning Agents
AI/ML Computational Science Associate Manager, Accenture
A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
Oct 24, 2025Abhijit Chatterjee, Niraj K. Jha, Jonathan D. Cohen +6Energy-Efficient ML Lifelong Learning Agents
School of Electrical and Computer Engineering, Georgia Institute of Technology · Department of Electrical and Computer Engineering, Princeton University · Department of Psychology & Neuroscience Institute, Princeton University +4

Jun 1, 2026J/K move · Enter open · S save

Position: Deployed Reinforcement Learning should be Continual

Parnian Behdin, Kevin Roice, Golnaz Mesbahi

Alberta Machine Intelligence Institute (Amii), Edmonton, Canada.

Non-Stationary RL Reinforcement Learning Lifelong Learning Agents Continual RL

Open paper AskPDF arXiv

Reinforcement Learning (RL) has received increasing attention and adoption in real-world use cases. Most of these systems follow a train-then-fix paradigm, where trained agents do not learn while interacting with the world until performance degrades and retraining becomes necessary. In this position paper, we argue that deploying an agent that is incapable of optimality, but receives an evaluative reward signal, is inherently a continual RL problem. We identify four sources of non-stationarity after deployment that necessitate never-ending learning, and highlight why the best deployed agents never stop adapting. We analyze successful examples of continual RL in the real world, and present the community with the advantages and measures to move away from the current train-then-fix paradigm.