mlsanityData to 7 Oct 2026

Continual Learning of Large Language Models: A Comprehensive Survey

arXiv 2404.16789 ↗First posted 25 Apr 2024cs.LG cs.AI cs.CLcited by 228

Not on the map. Why?

Cited by 29 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The recent success of large language models (LLMs) trained on static, pre-collected, general datasets has sparked numerous research directions and applications. One such direction addresses the non-trivial challenge of integrating pre-trained LLMs into dynamic data distributions, task structures, and user preferences. Pre-trained LLMs, when tailored for specific needs, often experience significant performance degradation in previous knowledge domains -- a phenomenon known as "catastrophic forgetting". While extensively studied in the continual learning (CL) community, it presents new manifestations in the realm of LLMs. In this survey, we provide a comprehensive overview of the current research progress on LLMs within the context of CL. This survey is structured into four main sections: we first describe an overview of continually learning LLMs, consisting of two directions of continuity: vertical continuity (or vertical continual learning), i.e., continual adaptation from general to specific capabilities, and horizontal continuity (or horizontal continual learning), i.e., continual adaptation across time and domains (Section 3). We then summarize three stages of learning LLMs in the context of modern CL: Continual Pre-Training (CPT), Domain-Adaptive Pre-training (DAP), and Continual Fine-Tuning (CFT) (Section 4). Then we provide an overview of evaluation protocols for continual learning with LLMs, along with the current available data sources (Section 5). Finally, we discuss intriguing questions pertaining to continual learning for LLMs (Section 6). The full list of papers examined in this survey is available at https://github.com/Wang-ML-Lab/llm-continual-learning-survey.

Key facts. Cited by 228 papers in the map (data through 7 Oct 2026). Builds on 282 of its 380 references that are in the map. First posted on arXiv 25 Apr 2024.

Builds on

282 of 380 references.

References · 282

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2023GPT-4 Technical Reportcited by 18,132
  6. 2022Training language models to follow instructions with human feedbackcited by 15,712
  7. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  8. 2017Proximal Policy Optimization Algorithmscited by 14,441
  9. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  10. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  11. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  12. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
38 more
  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2020Scaling Laws for Neural Language Modelscited by 6,411
  6. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  9. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  10. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  11. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  12. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  13. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  14. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  15. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  16. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  17. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  18. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  19. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  20. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  21. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  22. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  23. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  24. 2022Emergent Abilities of Large Language Modelscited by 2,483
  25. 2016Learning without Forgettingcited by 2,465
  26. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  27. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  28. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  29. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  30. 2019Language Models as Knowledge Bases?cited by 1,922
  31. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  32. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  33. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  34. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  35. 2019Towards VQA Models That Can Readcited by 1,696
  36. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  37. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  38. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413

50 most cited of 282 All 282 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 37; 2025: 75; 2026: 116.

228 papers.

Sort:

By area:

  1. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
  2. 2024On-Device Language Models: A Comprehensive Reviewcited by 101
  3. 2025Retaining by Doing: The Role of On-Policy Data in Mitigating Forgettingcited by 82
  4. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  5. 2024Towards Lifelong Learning of Large Language Models: A Surveycited by 60
  6. 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 56
  7. 2024BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Modelscited by 48
  8. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  9. 2026SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Taskscited by 45
  10. 2026Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agentscited by 44
  11. 2025Agentic Software Engineering: Foundational Pillars and a Research Roadmapcited by 40
  12. 2025Scaling Agents via Continual Pre-trainingcited by 39
38 more
  1. 2024ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detectioncited by 37
  2. 2024Mitigating Catastrophic Forgetting in Language Transfer via Model Mergingcited by 36
  3. 2026Doc-to-LoRA: Learning to Instantly Internalize Contextscited by 36
  4. 2025Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoningcited by 33
  5. 2025SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuningcited by 32
  6. 2025Activation-Informed Merging of Large Language Modelscited by 29
  7. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  8. 2025Narrow Finetuning Leaves Clearly Readable Traces in Activation Differencescited by 24
  9. 2024Unlocking Continual Learning Abilities in Language Modelscited by 22
  10. 2024Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Modelscited by 22
  11. 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practicescited by 22
  12. 2024LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Applicationcited by 21
  13. 2025MLLM-CL: Continual Learning for Multimodal Large Language Modelscited by 21
  14. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  15. 2024Surveying the MLLM Landscape: A Meta-Review of Current Surveyscited by 20
  16. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitiescited by 20
  17. 2024Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystackcited by 19
  18. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  19. 2025The Future of Continual Learning in the Era of Foundation Models: Three Key Directionscited by 16
  20. 2024LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Modelscited by 14
  21. 2024The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspectivecited by 14
  22. 2026Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgettingcited by 14
  23. 2024MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuningcited by 13
  24. 2025Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descentcited by 13
  25. 2025Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Modelscited by 13
  26. 2026Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learningcited by 13
  27. 2024Boundless Socratic Learning with Language Gamescited by 12
  28. 2025Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Modelscited by 12
  29. 2025Scalable Fingerprinting of Large Language Modelscited by 11
  30. 2025Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?cited by 11
  31. 2026How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessionscited by 11
  32. 2024Leveraging Large Language Models for Integrated Satellite-Aerial-Terrestrial Networks: Recent Advances and Future Directionscited by 10
  33. 2025Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Surveycited by 10
  34. 2025Continual Gradient Low-Rank Projection Fine-Tuning for LLMscited by 10
  35. 2025Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrievalcited by 10
  36. 2024Evaluating the External and Parametric Knowledge Fusion of Large Language Modelscited by 9
  37. 2025ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Thinkcited by 9
  38. 2025Continual Learning for Generative AI: From LLMs to MLLMs and Beyondcited by 9

50 most cited of 228 All 228 (JSON)