Towards an Agentic MAPE-K Architecture for Self-Adaptive Robotic Arm Systems

• Joaquim Ribeiro UECE
• Beatriz Andrade UECE
• Suyane Freitas UECE
• Lucas Alves UECE
• Paulo Henrique Maia UECE

DOI: https://doi.org/10.5753/se4as.2026.32834

Resumo

Robotic arm systems operate in dynamic and uncertain environments that require runtime adaptation. Although MAPE-K is widely used to structure self-adaptive systems, rule-based implementations often rely on predefined adaptation knowledge, limiting their ability to handle situations outside the anticipated adaptation space. This paper proposes an Agentic MAPE-K architecture for self-adaptive robotic arm systems, augmenting the Analyser and Planner with intelligent agents to support diagnosis and adaptation planning when predefined knowledge is insufficient. The architecture was instantiated as a proof of concept in a simulated robotic arm environment and examined using a single execution trace that encountered an obstacle whose height exceeded the anticipated range. After an initial predefined plan failed, the resulting runtime evidence supported an agent-assisted diagnosis and the reconsideration of available adaptation plans. Because an acceptable predefined alternative remained available, the complete fallback branch for generating a new plan was not exercised. The results therefore provide preliminary evidence of the feasibility of the proposed architectural integration and of using adaptation outcomes to inform subsequent MAPE-K decisions, rather than validation of end-to-end or agent-generated adaptation.

Palavras-chave: Self-Adaptive Systems, MAPE-K, Agentic AI, Robotic Arm Systems, Unanticipated Situations

Referências

Saeid Nahavandi et al. “Machine learning meets advanced robotic manipulation”. In: Information Fusion 105 (2024), p. 102221.

Gianluca Filippone et al. “Handling uncertainty in the specification of autonomous multi-robot systems through mission adaptation”. In: Proceedings of the 19th International Symposium on Software Engineering for Adaptive and Self-Managing Systems. 2024, pp. 25–36.

Hassan Sartaj et al. “Software engineering for self-adaptive robotics: A research agenda”. In: arXiv preprint arXiv:2505.19629 (2025).

DannyWeyns.An introduction to self-adaptive systems: A contemporary software engineering perspective. John Wiley & Sons, 2020.

Jeffrey O Kephart and David M Chess. “The vision of autonomic computing”. In: Computer 36.1 (2003), pp. 41–50.

Sara M Hezavehi et al. “Uncertainty in self-adaptive systems: A research community perspective”. In: ACM Transactions on Autonomous and Adaptive Systems (TAAS) 15.4 (2021), pp. 1–36.

Danny Weyns and Jesper Andersson. “From self-adaptation to self-evolution leveraging the operational design domain”. In: 2023 IEEE/ACM 18th Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS). IEEE. 2023, pp. 90–96.

Lei Wang et al. “A survey on large language model based autonomous agents”. In: Frontiers of Computer Science 18.6 (2024), p. 186345.

Xu Huang et al. “Understanding the planning of llm agents: A survey”. In: arXiv preprint arXiv:2402.02716 (2024).

Frank D Macías-Escrivá et al. “Self-adaptive systems: A survey of current approaches, research challenges and applications”. In: Expert Systems with Applications 40.18 (2013), pp. 7267–7279.

Didac Gil De La Iglesia and Danny Weyns. “MAPE-K formal templates to rigorously design behaviors for self-adaptive systems”. In: ACM Transactions on Autonomous and Adaptive Systems (TAAS) 10.3 (2015), pp. 1–31.

Diego Perez-Palacin and Raffaela Mirandola. “Uncertainties in the modeling of self-adaptive systems: a taxonomy and an example of availability evaluation”. In: Proceedings of the 5th ACM/SPEC International Conference on Performance Engineering. ICPE ’14. Dublin, Ireland: Association for Computing Machinery, 2014, pp. 3–14. isbn: 9781450327336. DOI: 10.1145/2568088.2568095.

Lucas Alves et al. “MAPER: Extending MAPE-K with LLM-Based Reasoning to Manage Unanticipated Situations in Self-Adaptive Systems”. In: Proceedings of the 21st International Conference on Software Engineering for Adaptive and Self-Managing Systems. SEAMS ’26. Rio de Janeiro, Brazil: Association for Computing Machinery, 2026, pp. 245–256. isbn: 979-8-4007-2445-9. DOI: 10.1145/3788550.3794886.

Divyansh Pandey et al. “POLARIS: Is Multi-Agentic Reasoning the Next Wave in Engineering Self-Adaptive Systems?” In: arXiv preprint arXiv:2512.04702 (2025).

Quentin Gallouédec et al. “panda-gym: Open-Source Goal-Conditioned Environments for Robotic Learning”. In: 4th Robot LearningWorkshop: Self-Supervised and Lifelong Learning at NeurIPS (2021).