Multi-Agent RAG for Autonomous Vehicles Using Decentralized Knowledge Graph on Blockchain

Sameer Misbah; Muhammad Farrukh Shahid; Shahbaz Siddiqui; M. Hassan Tanveer

Authors

Sameer Misbah FAST School of Computing, FAST-NUCES, Karachi
Muhammad Farrukh Shahid FAST School of Computing, FAST-NUCES, Karachi
Shahbaz Siddiqui FAST School of Computing, FAST-NUCES, Karachi
M. Hassan Tanveer Department of Robotics and Mechatronics Engineering, Kennesaw State University, Marietta, GA, USA

Keywords:

Autonomous Agricultural Vehicles, Agentic AI, Retrieval-Augmented Generation, Decentralized Knowledge Graph, Blockchain, Multi-Agent Systems

Abstract

Autonomous agricultural vehicles operate in dynamic environments where isolated learning and centralized coordination limit scalability and adaptability. To address this, the paper proposes a decentralized multi-agent Retrieval Augmented Generation (RAG) framework for autonomous farming vehicles that allows for collaborative real-time decision making via a blockchain-based distributed knowledge graph. Each vehicle node functions as an agentic entity that retrieves the validated field knowledge, such as current soil condition patterns, crop stress indicators, and the historical traversal results along with their outcomes from the shared knowledge graph, which are then integrated with the local sensory observations to then generate dynamic context-aware operational decisions. Blockchain provides a tamper-proof layer for knowledge integrity and authenticity, which ensures that the experiential updates are validated using lightweight consensus mechanisms before they are circulated, thereby preventing erroneous or malicious knowledge propagation. As opposed to existing blockchain-based agricultural solutions that focus primarily on data logging to prevent tampering and misuse, the proposed framework integrates blockchain directly into the agent's reasoning and learning loop. Experimental evaluation on a synthetically generated dataset of 5,000 interaction instances demonstrates that the proposed framework achieves a task success rate of 88.6%, compared to 81.0% for decentralized multi-agent baselines and 79.5% for centralized approaches. The framework further reduces latency by up to 28% while improving knowledge utilization by 10-19% and significantly lowering error propagation by up to 66%, indicating more stable and reliable decision-making, representing an improvement of approximately 9-11% over baseline methods. The results indicate that decentralized knowledge-driven reasoning can enhance the robustness and long-term learning in autonomous agricultural vehicle networks.

References

Qingchao Liu, Ruohan Yu, “Autonomous Driving in Agricultural Machinery: Advancing the Frontier of Precision Agriculture,” Actuators, vol. 14, no. 9, p. 464, 2025, doi: https://doi.org/10.3390/act14090464.

Dehua Zhang, Qingsong Yuan, Lei Meng, Ruixue Xia, Wei Liu & Chunbin Qin, “Reinforcement learning for single-agent to multi-agent systems: from basic theory to industrial application progress, a survey,” Artif. Intell. Rev., vol. 59, no. 46, 2026, [Online]. Available: https://link.springer.com/article/10.1007/s10462-025-11439-9

Z. Yang, N. Ma, and Y. Yao, “A Survey on Cooperative Control of Multi-Agent Systems,” Proc. - 2023 2nd Int. Conf. Artif. Intell. Human-Computer Interact. Robot. AIHCIR 2023, pp. 511–515, 2023, doi: 10.1109/AIHCIR61661.2023.00090.

D. K. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” arXiv:2005.11401, 2021, doi: https://doi.org/10.48550/arXiv.2005.11401.

Myeonghwa Lee, Seonho An, Min-Soo Kim, “PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers,” arXiv:2406.12430, 2024, [Online]. Available: https://arxiv.org/abs/2406.12430

Andrew Brown, Muhammad Roman, Barry Devereux, “A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges,” arXiv:2508.06401, 2025, [Online]. Available: https://arxiv.org/abs/2508.06401

Md Monjurul Karim, Dong Hoang Van, “AI Agents Meet Blockchain: A Survey on Secure and Scalable Collaboration for Multi-Agents,” Futur. Internet, vol. 17, no. 2, p. 57, 2025, doi: https://doi.org/10.3390/fi17020057.

J. Shen, H. Sheng, S. Wang, R. Cong, D. Yang, and Y. Zhang, “Blockchain-Based Distributed Multiagent Reinforcement Learning for Collaborative Multiobject Tracking Framework,” IEEE Trans. Comput., vol. 73, no. 3, pp. 778–788, Mar. 2024, doi: 10.1109/TC.2023.3343102.

“(PDF) Multi-Agent Coordination Strategies vs. Retrieval-Augmented Generation in LLMs: A Comparative Evaluation.” Accessed: May 05, 2026. [Online]. Available: https://www.researchgate.net/publication/398597083_Multi-Agent_Coordination_Strategies_vs_Retrieval-Augmented_Generation_in_LLMs_A_Comparative_Evaluation

“Multi-Agent RAG Framework for Entity Resolution: Advancing Beyond Single-LLM Approaches with Specialized Agent Coordination.” Accessed: May 06, 2026. [Online]. Available: https://www.mdpi.com/2073-431X/14/12/525

“Is Blockchain the Future of AI Alignment? Developing a Framework and a Research Agenda Based on a Systematic Literature Review.” Accessed: May 06, 2026. [Online]. Available: https://www.mdpi.com/2624-800X/5/3/50

“Retrieval-Augmented Generation to Generate Knowledge Assets and Creation of Action Drivers.” Accessed: May 06, 2026. [Online]. Available: https://www.researchgate.net/publication/397946484_Generative_AI_for_Sustainable_Smart_Environments_A_Review_of_Energy_Systems_Buildings_and_User-Centric_Decision-Making

Muhammad Murad, Muhammad Ahmed, “Agentic AI Framework to Automate Traditional Farming for Smart Agriculture,” AgriEngineering, vol. 8, no. 1, p. 8, 2026, doi: https://doi.org/10.3390/agriengineering8010008.

Z. Raza, I. U. Haq and M. Muneeb, “Agri-4-All: A Framework for Blockchain Based Agricultural Food Supply Chains in the Era of Fourth Industrial Revolution,” IEEE Access, vol. 11, pp. 29851–29867, 2023, doi: 10.1109/ACCESS.2023.3259962.

Mohamad Sheikho Al Jasem, Trevor De Clark, “Toward Decentralized Intelligence: A Systematic Literature Review of Blockchain-Enabled AI Systems,” Information, vol. 16, no. 9, p. 765, 2025, doi: https://doi.org/10.3390/info16090765.

“Technological Convergence of Blockchain and Artificial Intelligence: A Review and Challenges.” Accessed: May 06, 2026. [Online]. Available: https://www.mdpi.com/2079-9292/14/1/84

“Generative AI-Driven Smart Contract Optimization for Secure and Scalable Smart City Services.” Accessed: May 06, 2026. [Online]. Available: https://www.mdpi.com/2624-6511/8/4/118

Lavanya Ratnabala, Aleksey Fedoseev, Robinroy Peter, Dzmitry Tsetserukou, “MAGNNET: Multi-Agent Graph Neural Network-based Efficient Task Allocation for Autonomous Vehicles with Deep Reinforcement Learning,” arXiv:2502.02311, 2025, [Online]. Available: https://arxiv.org/abs/2502.02311

Yingxuan Yang, Huacan Chai, Shuai Shao, Yuanyi Song, Siyuan Qi, Renting Rui, Weinan Zhang, “AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems,” arXiv:2504.00587, 2025, [Online]. Available: https://arxiv.org/abs/2504.00587

“GRAG: Graph Retrieval-Augmented Generation - ACL Anthology.” Accessed: May 06, 2026. [Online]. Available: https://aclanthology.org/2025.findings-naacl.232/

M. T. Antony James, “Retrieval-Augmented Generation to Generate Knowledge Assets and Creation of Action Drivers,” Appl. Sci., vol. 15, no. 11, p. 6247, 2025, doi: https://doi.org/10.3390/app15116247.

Eugene Vorobiov, Ammar Jaleel Mahmood, Salim Rezvani, Robin Chhabra, “ARRC: Advanced Reasoning Robot Control - Knowledge-Driven Autonomous Manipulation Using Retrieval-Augmented Generation,” arXiv:2510.05547, 2025, [Online]. Available: http://arxiv.org/abs/2510.05547

Yayu Long, Kewei Chen, Long Jin, Mingsheng Shang, “DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics,” arXiv:2507.04661, 2025, [Online]. Available: https://arxiv.org/abs/2507.04661

Imran Kabir, Md Alimoor Reza, Syed Billah, “Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding,” arXiv:2503.12663, 2025, [Online]. Available: https://arxiv.org/abs/2503.12663

Quanting Xie, So Yeon Min, Pengliang Ji, Yue Yang, Tianyi Zhang, Kedi Xu, “Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation,” arXiv:2409.18313, 2024, [Online]. Available: https://arxiv.org/abs/2409.18313

Ketema Adere, Seble Hailu, Mesfin Abebe, Ararso Kemal, Semere W. Silassie, “A systematic review of artificial intelligence applications in Internet of Things, blockchain, and quantum cryptography,” Discov. Artif. Intell., vol. 6, no. 270, 2026, [Online]. Available: https://link.springer.com/article/10.1007/s44163-026-01029-1

Abhirup Khanna, Sapna Jain, “Generative AI and Blockchain-Integrated Multi-Agent Framework for Resilient and Sustainable Fruit Cold-Chain Logistics,” Foods, vol. 14, no. 17, p. 3004, 2025, doi: https://doi.org/10.3390/foods14173004.

Awid Vaziry, Sandro Rodriguez Garzon, Axel Küpper, “Towards Multi-Agent Economies: Enhancing the A2A Protocol with Ledger-Anchored Identities and x402 Micropayments for AI Agents,” arXiv:2507.19550, 2025, [Online]. Available: https://arxiv.org/abs/2507.19550

“What is Ollama? A Beginner’s Guide To This Platform.” Accessed: May 06, 2026. [Online]. Available: https://blog.udemy.com/what-is-ollama/

G. L. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, “LLaMA: Open and Efficient Foundation Language Models,” arXiv:2302.13971, 2023, doi: https://doi.org/10.48550/arXiv.2302.13971.

Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, “Alpaca: A Strong, Replicable Instruction-Following Model,” Stanford Univ. Press, 2023, [Online]. Available: https://crfm.stanford.edu/2023/03/13/alpaca.html

Philip Sun, David Simcha, Dave Dopson, Ruiqi Guo, Sanjiv Kumar, “SOAR: Improved Indexing for Approximate Nearest Neighbor Search,” arXiv:2404.00774, 2024, [Online]. Available: https://arxiv.org/abs/2404.00774