Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Enabling Agentic AI across the Cloud-Edge Computing Continuum: A Research Roadmap

, , , , , , , , , , , , ,

DOI: http://dx.doi.org/10.15439/2026F0210

Citation: Radu Prodan, , , , , , , , , , , , ,

Full text

Abstract. Agentic AI is shifting AI applications from passive model inference to goal-driven, tool-using, and collaborative autonomous systems. Yet, current deployments remain concentrated in data centers or powerful personal devices. This paper provides a research roadmap for enabling large-scale, enterprise-oriented agentic AI across the computing continuum, from cloud to edge, IoT, and emerging hardware platforms, where heterogeneity, mobility, energy constraints, and governance requirements fundamentally reshape agent design and operation. We argue for a continuum-native agent paradigm that decomposes agents into intelligence, persona, and memory, allowing their independent placement, migration, and replication. Building on this abstraction, we structure the open research space into three pillars (agent operation, agent connectivity, and agent trustworthiness) and elaborate on potential research directions and challenges. Finally, we outline evaluation directions grounded in representative industrial use cases and benchmarks. The roadmap aims to guide research and development toward enabling the deployment of agentic AI as first-class workloads on the cloud-edge continuum.

References

  1. “Autogen: A programming framework for agentic ai,” 2026. [Online]. Available: https://github.com/microsoft/autogen
  2. “Langgraph: Build resilient language agents as graphs,” 2026. [Online]. Available: https://github.com/langchain-ai/langgraph
  3. “Codex.” [Online]. Available: https://openai.com/blog/openai-codex/
  4. “Prism: A free workspace for scientific writing and collaboration, with gpt,” 2026. [Online]. Available: https://prism.openai.com/
  5. “Openclaw personal assistant agent,” 2026. [Online]. Available: https://github.com/openclaw/openclaw
  6. McKinsey. The state of AI in 2025: Agents, innovation, and transformation. [Online]. Available: https://www.mckinsey.com/ capabilities/quantumblack/our-insights/the-state-of-ai#/
  7. F.-X. Devailly, D. Larocque, and L. Charlin, “IG-RL: Inductive graph reinforcement learning for massive-scale traffic signal control,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 7, pp. 7496–7507, 2022.
  8. W. Jia and M. Ji, “Multi-agent deep reinforcement learning for largescale traffic signal control with spatio-temporal attention mechanism,” Applied Sciences, vol. 15, no. 15, p. 8605, 2025.
  9. Y. Liu, G. Luo, Q. Yuan, J. Li, L. Jin, B. Chen, and R. Pan, “GPLight: Grouped multi-agent reinforcement learning for large-scale traffic signal control.” in IJCAI, 2023, pp. 199–207.
  10. P. Patel, E. Choukse, C. Zhang, Í. Goiri, B. Warrier, N. Mahalingam, and R. Bianchini, “Polca: Power oversubscription in llm cloud providers,” arXiv preprint https://arxiv.org/abs/2308.12908, 2023.
  11. Q. Liu, D. Huang, M. Zapater, and D. Atienza, “GreenLLM: Sloaware dynamic frequency scaling for energy-efficient llm serving,” arXiv preprint arXiv:2508.16449, 2025.
  12. G. Wilkins, S. Keshav, and R. Mortier, “Hybrid heterogeneous clusters can lower the energy consumption of llm inference workloads,” in eEnergy’24, 2024, pp. 506–513.
  13. E. J. Husom, A. Goknil, L. K. Shar, and S. Sen, “The price of prompting: Profiling energy use in large language models inference,” arXiv preprint arXiv:2407.16893, 2024.
  14. M. Artetxe, S. Bhosale, N. Goyal, T. Mihaylov, M. Ott, S. Shleifer, X. V. Lin, J. Du, S. Iyer et al., “Efficient large scale language modeling with mixtures of experts,” arXiv preprint arXiv:2112.10684, 2021.
  15. D. Guo, D. Yang, H. Zhang, J. Song, P. Wang, Q. Zhu, R. Xu, R. Zhang, S. Ma, X. Bi et al., “Deepseek-r1 incentivizes reasoning in llms through reinforcement learning,” Nature, vol. 645, no. 8081, pp. 633–638, 2025.
  16. V. C. Pujol, B. Sedlak, T. Salvatori, K. Friston, and S. Dustdar, “Distributed intelligence in the computing continuum with active inference,” arXiv preprint arXiv:2505.24618, 2025.
  17. W. Chen, Z. You, R. Li, C. Qian, C. Zhao, C. Yang, R. Xie et al., “Internet of agents: Weaving a web of heterogeneous agents for collaborative intelligence,” in ICLR, 2025, pp. 36 374–36 411.
  18. W. Chen, Y. Su, J. Zuo, C. Yang, C. Yuan, C.-M. Chan, H. Yu, Y. Lu, Y.-H. Hung et al., “Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors,” in ICLR, 2024, pp. 20 094–20 136.
  19. Y. Du, S. Li, A. Torralba, J. B. Tenenbaum, and I. Mordatch, “Improving factuality and reasoning in language models through multiagent debate,” arXiv preprint arXiv:2305.14325, 2023.
  20. Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, “Edge intelligence: Paving the last mile of artificial intelligence with edge computing,” Proceedings of the IEEE, vol. 107, no. 8, pp. 1738–1762, 2019.
  21. Y. Mao, C. You, J. Zhang, K. Huang, and K. B. Letaief, “A survey on mobile edge computing: The communication perspective,” IEEE communications surveys & tutorials, vol. 19, no. 4, pp. 2322–2358, 2017.
  22. S. Bagchi, M.-B. Siddiqui, P. Wood, and H. Zhang, “Dependability in edge computing,” Communications of the ACM, vol. 63, no. 1, pp. 58– 66, 2019.
  23. C. He, G. Liu, S. Guo, and Y. Yang, “Privacy-preserving and low-latency federated learning in edge computing,” IEEE Internet of Things Journal, vol. 9, no. 20, pp. 20 149–20 159, 2022.
  24. F. A. Salaht, F. Desprez, and A. Lebre, “An overview of service placement problem in fog and edge computing,” ACM Computing Surveys, vol. 53, no. 3, pp. 1–35, 2020.
  25. Z. Zhong, M. Xu, M. A. Rodriguez, C. Xu, and R. Buyya, “Machine learning-based orchestration of containers: A taxonomy and future directions,” ACM Computing Surveys, vol. 54, no. 10s, pp. 1–35, 2022.
  26. A. Leivadeas and M. Falkner, “A survey on intent-based networking,” IEEE Communications Surveys & Tutorials, vol. 25, no. 1, pp. 625–655, 2022.
  27. D. Firmani, F. Leotta, J. G. Mathew, J. Rossi, L. Balzotti, H. Song, D. Roman, R. Dautov, E. J. Husom, S. Sen et al., “Intend: Intent-based data operation in the computing continuum,” in CAiSE’24, vol. 3692, 2024, pp. 43–50.
  28. B. Sedlak, V. C. Pujol, I. M. de Abril, P. K. Donta, A. N. Toosi, and S. Dustdar, “Service orchestration in the computing continuum: Structural challenges and vision,” IEEE Internet Computing, vol. 30, no. 2, pp. 88–98, 2026.
  29. T. Masterman, S. Besen, M. Sawtell, and A. Chao, “The landscape of emerging ai agent architectures for reasoning, planning, and tool calling: A survey,” arXiv preprint arXiv:2404.11584, 2024.
  30. W. Kwon, Z. Li, S. Zhuang, Y. Sheng, L. Zheng, C. H. Yu, J. Gonzalez, H. Zhang, and I. Stoica, “Efficient memory management for large language model serving with pagedattention,” in SOSP’23, 2023, pp. 611–626.
  31. M. Navardi, R. Aalishah, Y. Fu, Y. Lin, H. Li, Y. Chen, and T. Mohsenin, “Genai at the edge: Comprehensive survey on empowering edge devices,” in AAAI’25, vol. 5, no. 1, 2025, pp. 180–187.
  32. E. J. Husom, A. Goknil, M. Astekin, L. K. Shar, A. KÃ¥ sen, S. Sen, B. A. Mithassel, and A. Soylu, “Sustainable llm inference for edge ai: Evaluating quantized llms for energy efficiency, output accuracy, and inference latency,” ACM Transactions on Internet of Things, vol. 6, no. 4, pp. 1–35, 2025.
  33. K. Bhardwaj, “Pqv-mobile: A combined pruning and quantization toolkit to optimize vision transformers for mobile applications,” arXiv preprint arXiv:2408.08437, 2024.
  34. R. Agrawal, H. Kumar, and S. R. Lnu, “Efficient llms for edge devices: Pruning, quantization, and distillation techniques,” in ICMLAS, 2025, pp. 1413–1418.
  35. S. Al Abdul Wahid, A. Asad, and F. Mohammadi, “A survey on neuromorphic architectures for running artificial intelligence algorithms,” Electronics, vol. 13, no. 15, p. 2963, 2024.
  36. Model Context Protocol, “What is the Model Context Protocol (MCP)?” https://modelcontextprotocol.io/docs/getting-started/intro.
  37. Agentic AI foundation, https://aaif.io, accessed: 2026-02-12.
  38. Y. Yao, Z. Li, and H. Zhao, “Got: Effective graph-of-thought reasoning in language models,” in NAACL’24, 2024, pp. 2901–2921.
  39. D. Guo, D. Yang, H. Zhang, J. Song, P. Wang, Q. Zhu, R. Xu, R. Zhang, S. Ma, X. Bi et al., “Deepseek-r1 incentivizes reasoning in llms through reinforcement learning,” Nature, vol. 645, no. 8081, pp. 633–638, 2025.
  40. R. Prabhu, A. Nayak, J. Mohan, R. Ramjee, and A. Panwar, “vattention: Dynamic memory management for serving llms without pagedattention,” in ASPLOS’25, 2025, pp. 1133–1150.
  41. P. Letswalo, “MemGPT: Engineering semantic memory through adaptive retention and context summarization,” Information Matters, vol. 5, no. 10, 2025.
  42. Zep, “Agent memory at enterprise scale,” https://www.getzep.com/.
  43. Lightbend, Inc., “Akka: Build powerful reactive, distributed, and resilient message-driven applications,” https://akka.io.
  44. M. Etheredge, T. Fahringer, F. Erlacher, E. Kohler, S. Pedratscher, J. Aznar-Poveda, N. Saurabh, and A. Lebre, “Collaborative state machines: A better programming model for the cloud-edge-iot continuum,” arXiv preprint arXiv:2507.21685, 2025.
  45. Q. Wang and D. Oswald, “Confidential computing on heterogeneous cpu-gpu systems: Survey and future directions,” ACM Computing Surveys, 2026.
  46. Q. Zhu, S. W. Loke, R. Trujillo-Rasua, F. Jiang, and Y. Xiang, “Applications of distributed ledger technologies to the internet of things: A survey,” ACM computing surveys, vol. 52, no. 6, pp. 1–34, 2019.
  47. I. O. Gallegos, R. A. Rossi, J. Barrow, M. M. Tanjim, S. Kim, F. Dernoncourt, T. Yu, R. Zhang, and N. K. Ahmed, “Bias and fairness in large language models: A survey,” Computational linguistics, vol. 50, no. 3, pp. 1097–1179, 2024.
  48. S. Ghosh-Dastidar and H. Adeli, “Spiking neural networks,” International journal of neural systems, vol. 19, no. 04, pp. 295–308, 2009.
  49. N. Kasabov, K. Dhoble, N. Nuntalid, and G. Indiveri, “Dynamic evolving spiking neural networks for on-line spatio-and spectro-temporal pattern recognition,” Neural Networks, vol. 41, pp. 188–201, 2013.
  50. D. Marković, A. Mizrahi, D. Querlioz, and J. Grollier, “Physics for neuromorphic computing,” Nature Reviews Physics, vol. 2, no. 9, pp. 499–510, 2020.
  51. S. Goldstein and C. D. Kirk-Giannini, “A case for ai consciousness: Language agents and global workspace theory,” arXiv preprint arXiv:2410.11407, 2024.
  52. EUCloudEdgeIoT, “Research & Innovation Roadmap,” https://eucloudedgeiot.eu/research-innovation-roadmap/.
  53. H. Kokkonen, L. Lovén, N. H. Motlagh, A. Kumar, J. Partala, T. Nguyen, V. C. Pujol, P. Kostakos et al., “Autonomy and intelligence in the computing continuum: Challenges, enablers, and future directions for orchestration,” arXiv preprint arXiv:2205.01423, 2022.
  54. R. Sapkota, K. I. Roumeliotis, and M. Karkee, “Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges,” Information Fusion, p. 103599, 2025.
  55. D. Amalfitano, A. Metzger, M. Autili, T. Fulcini, T. Hey, J. Keim et al., “A research roadmap for augmenting software engineering processes and software products with generative ai,” ACM TOSEM, 2026.
  56. “Amazon bedrock,” Amazon Web Services product page. [Online]. Available: https://aws.amazon.com/bedrock/
  57. “Azure openai service.” [Online]. Available: https://learn.microsoft.com/ en-us/azure/ai-services/openai/overview
  58. “Vertex ai generative ai,” Google Cloud documentation. [Online]. Available: https://cloud.google.com/vertex-ai/generative-ai/docs/overview
  59. “Ollama.” [Online]. Available: https://github.com/ollama/ollama
  60. Agent skills. [Online]. Available: https://agentskills.io/home
  61. European Commission, “Cognitive Computing Continuum for LargeScale Distributed GenAI Agents (CoAgent),” CORDIS: EU Research Results, 2026, horizon Europe project, Grant agreement ID: 101297191. [Online]. Available: https://cordis.europa.eu/project/id/101297191