mlsanityData to 14 Oct 2026

Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmap

arXiv 2512.04680 ↗First posted 4 Dec 2025cs.SE cs.AI cs.HCcited by 5

Not on the map. Why?

Abstract (arXiv)

Self-adaptive systems (SASs) are designed to handle changes and uncertainties through a feedback loop with four core functionalities: monitoring, analyzing, planning, and execution. Recently, generative artificial intelligence (GenAI), especially the area of large language models, has shown impressive performance in data comprehension and logical reasoning. These capabilities are highly aligned with the functionalities required in SASs, suggesting a strong potential to employ GenAI to enhance SASs. However, the specific benefits and challenges of employing GenAI in SASs remain unclear. Yet, providing a comprehensive understanding of these benefits and challenges is complex due to several reasons: limited publications in the SAS field, the technological and application diversity within SASs, and the rapid evolution of GenAI technologies. To that end, this paper aims to provide researchers and practitioners a comprehensive snapshot that outlines the potential benefits and challenges of employing GenAI's within SAS. Specifically, we gather, filter, and analyze literature from four distinct research fields and organize them into two main categories to potential benefits: (i) enhancements to the autonomy of SASs centered around the specific functions of the MAPE-K feedback loop, and (ii) improvements in the interaction between humans and SASs within human-on-the-loop settings. From our study, we outline a research roadmap that highlights the challenges of integrating GenAI into SASs. The roadmap starts with outlining key research challenges that need to be tackled to exploit the potential for applying GenAI in the field of SAS. The roadmap concludes with a practical reflection, elaborating on current shortcomings of GenAI and proposing possible mitigation strategies.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 58 of its 107 references that are in the map. First posted on arXiv 4 Dec 2025.

Builds on

58 of 107 references.

References · 58

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  6. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  7. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  8. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  9. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 268
  10. 2023Using an LLM to Help With Code Understandingcited by 228
  11. 2023PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Predictioncited by 137
  12. 2022Few-shot training LLMs for project-specific code-summarizationcited by 129
38 more
  1. 2023Baldur: Whole-Proof Generation and Repair with Large Language Modelscited by 119
  2. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  3. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Modelscited by 98
  4. 2023Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysiscited by 92
  5. 2023Fuzz4All: Universal Fuzzing with Large Language Modelscited by 88
  6. 2023ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testingcited by 88
  7. 2023Getting pwn'd by AI: Penetration Testing with Large Language Modelscited by 83
  8. 2023DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Modelscited by 81
  9. 2023Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)cited by 72
  10. 2023Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learningcited by 72
  11. 2023Large Language Models for Test-Free Fault Localizationcited by 67
  12. 2022Enabling Conversational Interaction with Mobile UI using Large Language Modelscited by 66
  13. 2023Graphologue: Exploring Large Language Model Responses with Interactive Diagramscited by 66
  14. 2023GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysiscited by 65
  15. 2021Personalized Transformer for Explainable Recommendationcited by 59
  16. 2023Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repaircited by 55
  17. 2023Prompt-Enhanced Software Vulnerability Detection Using ChatGPTcited by 51
  18. 2023SayCanPay: Heuristic Planning with Large Language Models using Learnable Domain Knowledgecited by 49
  19. 2024Large Language Model for Vulnerability Detection: Emerging Results and Future Directionscited by 45
  20. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 44
  21. 2023Interpretable Online Log Analysis Using Large Language Models with Prompt Strategiescited by 38
  22. 2022Automatic Code Documentation Generation Using GPT-3cited by 37
  23. 2023Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledgecited by 32
  24. 2024LLMParser: An Exploratory Study on Using Large Language Models for Log Parsingcited by 32
  25. 2020Generating Accurate Assert Statements for Unit Test Cases using Pretrained Transformerscited by 30
  26. 2022SOS: Score-based Oversampling for Tabular Datacited by 29
  27. 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agentscited by 29
  28. 2023PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refinecited by 28
  29. 2023Natural Language Dataset Generation Framework for Visualizations Powered by Large Language Modelscited by 20
  30. 2022CIRCLE: Continual Repair across Programming Languagescited by 17
  31. 2023GrACE: Generation using Associated Code Editscited by 16
  32. 2021Fast Changeset-based Bug Localization with BERTcited by 13
  33. 2022Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planningcited by 10
  34. 2022A Generative Approach for Script Event Prediction via Contrastive Fine-tuningcited by 9
  35. 2023Automatic Generation of Test Cases based on Bug Reports: a Feasibility Study with Large Language Modelscited by 8
  36. 2024Automatic Histograms: Leveraging Language Models for Text Dataset Explorationcited by 8
  37. 2021Applying Machine Learning in Self-Adaptive Systems: A Systematic Literature Reviewcited by 7
  38. 2024Exploring the Potential of Large Language Models in Self-adaptive Systemscited by 7

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Agents in the Large: Perception-Centered Architecture for Persistent Agentscited by 1
  2. 2026Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summariescited by 0
  3. 2026Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memorycited by 0
  4. 2026Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systemscited by 0
  5. 2026CoAdapt: An LLM-based Framework for Adaptive Collaborative Perception in IIoT Robotic Swarmscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative AI for Software Architecture. Applications, Challenges, and Future Directions
  2. 2025Generative to Agentic AI: Survey, Conceptualization, and Challenges
  3. 2024Generative AI Systems: A Systems-based Perspective on Generative AI
  4. 2026Evaluating adaptive and generative AI-based feedback and recommendations in a knowledge-graph-integrated programming learning system
  5. 2024Facilitating Human Feedback for GenAI Prompt Optimization
  6. 2024Review of Generative AI Methods in Cybersecurity
  7. 2025Survey of GenAI for Automotive Software Development: From Requirements to Executable Code
  8. 2024A Primer on Generative AI for Telecom: From Theory to Practice