Communication-Efficient Networking for Distributed Agentic AI: A Systematic Review of Protocols, Coordination, Latency and Energy Consumption

Abstract

Distributed agentic artificial intelligence increasingly relies on networked groups of autonomous agents that exchange observations, intentions, plans and task states to achieve collective goals. This systematic review synthesizes peer-reviewed studies published between 2023 and 2026 on communication-efficient networking for distributed agentic AI, multi-agent reinforcement learning and networked autonomous systems. Following PRISMA 2020, studies were identified from major scholarly databases and analyzed thematically across communication protocols, message compression and selection, semantic communication, coordination mechanisms, latency reduction, energy efficiency and deployment challenges. The evidence shows that selective engagement, graph-based compression, delay-aware communication, implicit consensus and value-of-information scheduling can reduce redundant exchanges while maintaining coordination quality. Semantic and edge–cloud approaches further lower payload size and local computational demand, although their benefits depend on channel conditions, resource availability and task placement. Persistent limitations include scalability, protocol interoperability, security and privacy risks, inconsistent energy reporting, dependence on simulated environments and limited standardization of evaluation metrics. The review concludes that communication efficiency should be treated as a joint optimization problem involving bandwidth, latency, computation, energy and task performance. Future research should prioritize interoperable protocols, adaptive communication topologies, secure message exchange, realistic testbeds and standardized reporting frameworks for dependable, scalable and sustainable distributed agentic systems at scale.

Keywords

• Agentic artificial intelligence
• communication efficiency
• distributed multi-agent systems
• latency and energy optimization
• semantic communication

Dağıtık Etmenli Yapay Zekâda İletişim Verimli Ağ Oluşturma: Protokoller, Koordinasyon, Gecikme ve Enerji Tüketimi Üzerine Sistematik Bir Derleme

Abstract

Dağıtık etmenli yapay zekâ, ortak hedeflere ulaşmak amacıyla gözlem, niyet, plan ve görev durumlarını paylaşan ağ bağlantılı özerk etmen gruplarına giderek daha fazla dayanmaktadır. Bu sistematik derleme, 2023–2026 yılları arasında yayımlanan ve dağıtık etmenli yapay zekâ, çok etmenli pekiştirmeli öğrenme ve ağ bağlantılı özerk sistemlerde iletişim verimli ağ oluşturmayı inceleyen hakemli çalışmaları sentezlemektedir. PRISMA 2020 çerçevesi izlenerek çalışmalar başlıca akademik veri tabanlarından belirlenmiş; iletişim protokolleri, mesaj sıkıştırma ve seçimi, anlamsal iletişim, koordinasyon mekanizmaları, gecikmenin azaltılması, enerji verimliliği ve dağıtım zorlukları açısından tematik olarak analiz edilmiştir. Bulgular, seçici etkileşim, grafik tabanlı sıkıştırma, gecikme farkındalıklı iletişim, örtük uzlaşma ve bilgi değeri temelli zamanlamanın koordinasyon kalitesini korurken gereksiz iletişimleri azaltabildiğini göstermektedir. Anlamsal ve uç–bulut yaklaşımları, veri yükü boyutunu ve yerel hesaplama gereksinimini daha da azaltmaktadır; ancak bu avantajlar kanal koşullarına, kaynak kullanılabilirliğine ve görev yerleşimine bağlıdır. Süregelen sınırlılıklar arasında ölçeklenebilirlik, protokol birlikte çalışabilirliği, güvenlik ve gizlilik riskleri, enerji raporlamasındaki tutarsızlıklar, benzetim ortamlarına bağımlılık ve değerlendirme ölçütlerinin sınırlı ölçüde standartlaştırılması bulunmaktadır. Derleme, iletişim verimliliğinin bant genişliği, gecikme, hesaplama, enerji ve görev performansını kapsayan ortak bir optimizasyon problemi olarak ele alınması gerektiği sonucuna varmaktadır. Gelecekteki araştırmalar; güvenilir, ölçeklenebilir ve sürdürülebilir dağıtık etmenli sistemler için birlikte çalışabilir protokollere, uyarlanabilir iletişim topolojilerine, güvenli mesajlaşmaya, gerçekçi test ortamlarına ve standartlaştırılmış raporlama çerçevelerine öncelik vermelidir.

Keywords

• Etmenli yapay zekâ
• iletişim verimliliği
• dağıtık çok etmenli sistemler
• gecikme ve enerji optimizasyonu
• anlamsal iletişim

References

1. Allmendinger, S., Bonenberger, L., & Kühl, N. (2026). Multi-agent AI. Electronic Markets, 36, Article 18. https://doi.org/10.1007/s12525-025-00862-z
2. Chen, W., Su, Y., Zuo, J., Yang, C., Yuan, C., Chan, C.-M., Yu, H., Lu, Y., Hung, Y.-H., Qian, C., Qin, Y., Cong, X., Xie, R., Liu, Z., Sun, M., & Zhou, J. (2024). AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors. Proceedings of the International Conference on Learning Representations.
3. Ding, L., Lyu, T., Bi, Z., Wang, H., Feng, S., & Yu, W. (2026). Communication-efficient multi-agent reinforcement learning with spatiotemporal information hub. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 20799–20807.
4. Ding, S., Du, W., Ding, L., Guo, L., & Zhang, J. (2024). Learning efficient and robust multi-agent communication via graph information bottleneck. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 17346–17353.
5. Fan, Y., Zhang, J., Cai, K., Yang, J., Tang, C., Wang, J., & Wang, K. (2026). Cost-effective communication: An auction-based method for language agent interaction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29412–29420.
6. Gao, Z., Liang, H., Hao, Y., Hao, L., & Ke, L. (2026). GRDC: A unified graph-driven framework for role discovery and communication in multi-agent reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29441–29449.
7. He, P., Lin, Y., Dong, S., Xu, H., Xing, Y., & Liu, H. (2025). Red-teaming LLM multi-agent systems via communication attacks. In Findings of the Association for Computational Linguistics: ACL 2025 (pp. 6726–6747). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.findings-acl.349
8. Ji, Z., & Qin, Z. (2024). Computational offloading in semantic-aware cloud-edge-end collaborative networks. IEEE Journal of Selected Topics in Signal Processing, 18(7), 1235–1248.

9. Kavathekar, I., Jain, H., Rathod, A., Kumaraguru, P., & Ganu, T. (2026). TAMAS: Benchmarking adversarial risks in multi-agent LLM systems. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (pp. 31238–31268). Association for Computational Linguistics. https://doi.org/10.18653/v1/2026.acl-long.1442
10. Li, D., Lou, N., Xu, Z., Zhang, B., & Fan, G. (2025). Efficient communication in multi-agent reinforcement learning with implicit consensus generation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), 23240–23248. https://doi.org/10.1609/aaai.v39i22.34490
11. Li, G., Hammoud, H. A. A. K., Itani, H., Khizbullin, D., & Ghanem, B. (2023). CAMEL: Communicative agents for “mind” exploration of large language model society. Advances in Neural Information Processing Systems, 36.
12. Li, X., & Zhang, J. (2024). Context-aware communication for multi-agent reinforcement learning. In Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (pp. 1156–1164). International Foundation for Autonomous Agents and Multiagent Systems.
13. Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., Yang, K., Zhang, S., Deng, X., Zeng, A., Du, Z., Zhang, C., Shen, S., Zhang, T., Su, Y., Sun, H., Huang, M., Dong, Y., & Tang, J. (2024). AgentBench: Evaluating LLMs as agents. In Proceedings of the Twelfth International Conference on Learning Representations.
14. Liu, Z., Li, Y., Wang, J., Tu, J., Hong, Y., Li, F., Liu, Y., Sugawara, T., & Tang, Y. (2026). Robust and efficient communication in multi-agent reinforcement learning. Chaos, 36(2), Article 022101. https://doi.org/10.1063/5.0303916
15. Ma, C., Zhang, J., Zhu, Z., Yang, C., Yang, Y., Jin, Y., Lan, Z., Kong, L., & He, J. (2024). AgentBoard: An analytical evaluation board of multi-turn LLM agents. Advances in Neural Information Processing Systems, 37, 74325–74362.
16. Maciel, R. S. P., Valle, P. H. D., Santos, K. S., & Nakagawa, E. Y. (2024). Systems interoperability types: A tertiary study. ACM Computing Surveys, 56(10), 1–37. https://doi.org/10.1145/3659098
17. Meng, X., & Tan, Y. (2024). PMAC: Personalized multi-agent communication. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 17505–17513.
18. Pati, A. K. (2025). Agentic AI: A comprehensive survey of technologies, applications, and societal implications. IEEE Access, 13, 151824–151837. https://doi.org/10.1109/ACCESS.2025.3585609
19. Song, S., Lin, Y., Han, S., Yao, C., Wu, H., Wang, S., & Lv, K. (2025). CoDe: Communication delay-tolerant multi-agent collaboration via dual alignment of intent and timeliness. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), 23304–23312. https://doi.org/10.1609/aaai.v39i22.34497
20. Sun, C., He, P., Ji, Q., Zang, Z., Li, J., Wang, R., & Wang, W. (2026). M2I2: Learning efficient multi-agent communication via masked state modeling and intention inference. Proceedings of the AAAI Conference on Artificial Intelligence, 40(30), 25672–25681.
21. Sun, C., Zang, Z., Li, J., Li, J., Xu, X., Wang, R., & Zheng, C. (2024). T2MAC: Targeted and trusted multi-agent communication through selective engagement and evidence-driven integration. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 15154–15163.
22. Tarasova, E., Erofeeva, V., Granichin, O., & Chernikov, K. (2025). Decentralized adaptive task allocation for dynamic multi-agent systems. Scientific Reports, 15, Article 39226.
23. Wang, S., Zhang, G., Yu, M., Wan, G., Meng, F., Guo, C., Wang, K., & Wang, Y. (2025). G-Safeguard: A topology-guided security lens and treatment on LLM-based multi-agent systems. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (pp. 7261–7276). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.acl-long.359
24. Wang, X., Li, X., Shao, J., & Zhang, J. (2023). AC2C: Adaptively controlled two-hop communication for multi-agent reinforcement learning. In Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (pp. 427–435). International Foundation for Autonomous Agents and Multiagent Systems.
25. Xie, S., Li, H., Wang, Z., Song, S., Zhang, J., & Letaief, K. B. (2026). Towards reasoning-empowered task-oriented communication for agent networks. npj Wireless Technology, 2, Article 25.
26. Yu, J., Jia, J., Qin, S., Jia, X., Ma, S., Huang, Y., Yuan, Y., & Cheng, G. (2026). MPAS: Breaking sequential constraints of multi-agent communication topologies via individual-epistemic message propagation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29847–29855. https://doi.org/10.1609/aaai.v40i35.40231
27. Yuan, T., Chung, H.-M., Yuan, J., & Fu, X. (2023). DACOM: Learning delay-aware communication for multi-agent reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 37(10), 11763–11771.
28. Zhang, Q., Sun, Z., Zhang, Y., Yu, Z., Guo, B., & Zhang, J. (2026). VIL2C: Value-of-information-aware low-latency communication for multi-agent reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29874–29882.
29. Zhang, X., Hou, D., Xiong, Z., Liu, Y., Wang, S., & Li, Y. (2025). EALLR: Energy-aware low-latency routing data-driven model in mobile edge computing. IEEE Transactions on Consumer Electronics, 71(2), 6612–6626.