mlsanityData to 14 Oct 2026

AI Autonomy : Self-Initiated Open-World Continual Learning and Adaptation

arXiv 2203.08994 ↗First posted 17 Mar 2022cs.AI cs.CL cs.HCcited by 23

Not on the map. Why?

Abstract (arXiv)

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being retrained offline periodically on the initiation of human engineers and (2) accommodate or adapt to unexpected or novel circumstances. As the real-world is an open environment that is full of unknowns or novelties, the capabilities of detecting novelties, characterizing them, accommodating/adapting to them, gathering ground-truth training data and incrementally learning the unknowns/novelties become critical in making the AI agent more and more knowledgeable, powerful and self-sustainable over time. The key challenge here is how to automate the process so that it is carried out continually on the agent's own initiative and through its own interactions with humans, other agents and the environment just like human on-the-job learning. This paper proposes a framework (called SOLA) for this learning paradigm to promote the research of building autonomous and continual learning enabled AI agents. To show feasibility, an implemented agent is also described.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 22 of its 73 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

22 of 73 references.

References · 22

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  3. 2016Progressive Neural Networkscited by 1,361
  4. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  5. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  6. 2017Continual Learning with Deep Generative Replaycited by 1,158
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  8. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
  9. 2020A Survey of Deep Active Learningcited by 554
  10. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 286
  11. 2014Towards Open World Recognitioncited by 226
  12. 2020Using Hindsight to Anchor Past Knowledge in Continual Learningcited by 161
10 more
  1. 2020Deep Learning for Anomaly Detection: A Reviewcited by 159
  2. 2021Achieving Forgetting Prevention and Knowledge Transfer in Continual Learningcited by 91
  3. 2021Continual Learning of a Mixed Sequence of Similar and Dissimilar Taskscited by 81
  4. 2018Open-world Learning and Application to Product Classificationcited by 39
  5. 2021Open-world Machine Learning: Applications, Challenges, and Opportunitiescited by 34
  6. 2020CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directionscited by 26
  7. 2019Interactive Open-Ended Object, Affordance and Grasp Learning for Robotic Manipulationcited by 6
  8. 2019Intrinsic motivations and open-ended learningcited by 6
  9. 2019Lifelong and Interactive Learning of Factual Knowledge in Dialoguescited by 3
  10. 2020Data-Driven Hierarchical Predictive Learning in Unknown Environmentscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 10; 2026: 5.

23 papers.

Sort:

By area:

  1. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  2. 2025Fully Autonomous AI Agents Should Not be Developedcited by 45
  3. 2023Learnability and Algorithm for Continual Learningcited by 28
  4. 2023Open-World Continual Learning: Unifying Novelty Detection and Continual Learningcited by 22
  5. 2024Continual Learning for Smart City: A Surveycited by 9
  6. 2024Position: Foundation Agents as the Paradigm Shift for Decision Makingcited by 9
  7. 2024CLoG: Benchmarking Continual Learning of Image Generation Modelscited by 5
  8. 2023A Domain-Independent Agent Architecture for Adaptive Operation in Evolving Open Worldscited by 3
  9. 2025Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptationcited by 3
  10. 2025AI Must not be Fully Autonomouscited by 3
  11. 2024Over the Edge of Chaos? Excess Complexity as a Roadblock to Artificial General Intelligencecited by 2
  12. 2025Text Classification Under Class Distribution Shift: A Surveycited by 2
11 more
  1. 2025Improving Open-world Continual Learning under the Constraints of Scarce Labeled Datacited by 2
  2. 2025From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communicationscited by 2
  3. 2025A cybersecurity AI agent selection and decision support frameworkcited by 0
  4. 2025Information Theory in Open-world Machine Learning Foundations, Frameworks, and Future Directioncited by 0
  5. 2025Learning After Model Deploymentcited by 0
  6. 2025What's the next frontier for Data-centric AI? Data Savvy Agentscited by 0
  7. 2026MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text Categorizationcited by 0
  8. 2026Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Roboticscited by 0
  9. 2026MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognitioncited by 0
  10. 2026HyperDCM: Dynamic Cluster Memory Replay in Hyperbolic Space for Continual Robotic Navigation Across Scenescited by 0
  11. 2026NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Expertscited by 0