Document Open Access Logo

A Silent Multi-Agent Recommendation Engine with Graph-Augmented Memory for Immersive B2B E-Commerce

Authors Davi Silva Eleuterio , Pedro Filipe Oliveira , Paulo Matos

PDF

File

Thumbnail PDF
PDF
OASIcs.SLATE.2026.15.pdf
  • Filesize: 1.33 MB
  • 14 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Applied computing → Document analysis
  • Computing methodologies → Information extraction
  • Computing methodologies → Machine learning
Keywords
  • multi-agent systems
  • agentic RAG
  • product recommendation
  • LangGraph

Metrics

Abstract

Currently, e-commerce platforms are transitioning from static 2D catalogues to immersive environments, requiring recommendation systems to process complex behavioural signals. Traditional collaborative filtering struggles with cold-start scenarios and lacks semantic understanding of product catalogues. This paper presents a silent multi-agent recommendation engine developed for the VIMOS (Virtual Integrated Market Online Shopping) project, designed to operate without explicit textual input. Orchestrated via a LangGraph Directed Acyclic Graph, the system utilises Agentic Retrieval-Augmented Generation (RAG) to dynamically synthesise behavioural signals, dense vector retrieval (Qdrant), and knowledge graph traversal (Apache AGE). A locally hosted Llama 3.1 8B model autonomously extracts implicit user preferences to update a persistent graph database and generates deterministic, human-readable explanations for each recommendation. A two-shot verifier engineering pattern is introduced to resolve the structural incompatibility between dynamic candidate sets and static graph execution. The architecture is validated using a controlled synthetic dataset of B2B industrial products - sufficient for functional validation of all agent routing paths - demonstrating high retrieval accuracy, strict constraint adherence (stock and availability verification), and sub-4-second end-to-end latency (when the generative semantic justification step is bypassed) with no external API dependencies.

Cite As Get BibTex

Davi Silva Eleuterio, Pedro Filipe Oliveira, and Paulo Matos. A Silent Multi-Agent Recommendation Engine with Graph-Augmented Memory for Immersive B2B E-Commerce. In 15th Symposium on Languages, Applications and Technologies (SLATE 2026). Open Access Series in Informatics (OASIcs), Volume 144, pp. 15:1-15:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026) https://doi.org/10.4230/OASIcs.SLATE.2026.15

Author Details

Davi Silva Eleuterio
  • CeDRI, SusTEC, Instituto Politécnico de Bragança, Portugal
Pedro Filipe Oliveira
  • CeDRI, SusTEC, Instituto Politécnico de Bragança, Portugal
Paulo Matos
  • CeDRI, SusTEC, Instituto Politécnico de Bragança, Portugal

Funding

This work was supported by FCT - Fundacão para a Ciência e Tecnologia, I.P. by projects: CeDRI, UID/05757/2025 (DOI: https://doi.org/10.54499/UID/05757/2025) and UID/PRR/05757/2025 (DOI: https://doi.org/10.54499/UID/PRR/05757/2025); SusTEC, LA/P/0007/2020 (DOI: https://doi.org/10.54499/LA/P/0007/2020) and by NORTE2030-FEDER-02214300 - "VIMOS – Virtual Integrated Market Online Shopping", through the Fundo Europeu de Desenvolvimento Regional (FEDER) and Programa Regional do Norte (Norte 2030) do Portugal 2030.

References

  1. Gustavo Aquino, Nádila Azevedo, Leandro Okimoto, Leonardo Camelo, Hendrio Bragça, Rubens Fernandes, André Printes, Fábio Cardoso, Raimundo Gomes, and I. Gondres. From RAG to Multi-Agent Systems: A Survey of Modern Approaches in LLM Development, February 2025. URL: https://doi.org/10.20944/preprints202502.0406.v1.
  2. Mohannad Moufeed Ayyash and Hala Montaser Mohammad Ali. Human-computer interaction meets consumer psychology: How augmented reality shapes decision styles in online fashion purchases. Computers in Human Behavior Reports, 21:100985, 2026. URL: https://doi.org/10.1016/j.chbr.2026.100985.
  3. Gautam B and Anupam Purwar. Evaluating the Efficacy of Open-Source LLMs in Enterprise-Specific RAG Systems: A Comparative Study of Performance and Scalability, June 2024. arXiv:2406.11424 [cs]. URL: https://doi.org/10.48550/arXiv.2406.11424.
  4. Wan Chong Choi and Chi In Chang. Advantages and Limitations of Open-Source versus Commercial Large Language Models (LLMs): A Comparative Study of DeepSeek and OpenAI’s ChatGPT, March 2025. URL: https://doi.org/10.20944/preprints202503.1081.v1.
  5. Davi Silva Eleuterio, Pedro Filipe Oliveira, Paulo Matos, and Jorge Manuel Afonso Alves. A chatbot to help promoting financial literacy. In Proceedings of the 14th Symposium on Languages, Applications and Technologies (SLATE 2025), OASIcs, 2025. Same authors, prior conference paper. URL: https://doi.org/10.4230/OASIcs.SLATE.2025.7.
  6. Mohamed Fezari and Ali Al Dahoud. The Evolution of Retrieval-Augmented Generation (RAG) in AI, January 2026. URL: https://doi.org/10.13140/RG.2.2.27107.62245.
  7. Xiaopeng Li, Pengyue Jia, Derong Xu, Yi Wen, Yingyi Zhang, Wenlin Zhang, Wanyu Wang, Yichao Wang, Zhaocheng Du, Xiangyang Li, Yong Liu, Huifeng Guo, Ruiming Tang, and Xiangyu Zhao. A Survey of Personalization: From RAG to Agent, April 2025. arXiv:2504.10147 [cs]. URL: https://doi.org/10.48550/arXiv.2504.10147.
  8. Jintao Liang, Gang Su, Huifeng Lin, You Wu, Rui Zhao, and Ziyue Li. Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges, June 2025. arXiv:2506.10408 [cs]. URL: https://doi.org/10.48550/arXiv.2506.10408.
  9. Haitao Lu, Dayu Zheng, and Luo Yang. Mutual information-based retrieval-augmented generation for domain question answering. Knowledge and Information Systems, 68:49, January 2026. URL: https://doi.org/10.1007/s10115-025-02624-x.
  10. Merylin Monaro, Alice Bettelli, Giovanni Portello, Leonardo Pierobon, Valeria Orso, Ariel Caputo, Maria Luisa Campanini, Andrea Giachetti, and Luciano Gamberini. Enhancing shopping experience in augmented reality by customizing product manipulation modalities: A customer experience study. International Journal of Human-Computer Studies, 202:103553, 2025. URL: https://doi.org/10.1016/j.ijhcs.2025.103553.
  11. Rahul Mundlamuri, Ganesh Reddy Gunnam, Nikhil Kumar Mysari, and Jayakanth Pujuri. The Evolution of AI: From Classical Machine Learning to Modern Large Language Models. IEEE Access, 13:178302-178341, 2025. URL: https://doi.org/10.1109/ACCESS.2025.3621344.
  12. R. Pugliese, G. Kourousias, F. Venier, and G. Garlatti Costa. Agentic publications: redesigning scientific publishing in the age of thinking large language models. Journal of Documentation, 82(7):125-149, 2026. URL: https://doi.org/10.1108/JD-07-2025-0207.
  13. Ranjan Sapkota, Konstantinos I. Roumeliotis, and Manoj Karkee. AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges. Information Fusion, 126:103599, February 2026. URL: https://doi.org/10.1016/j.inffus.2025.103599.
  14. Aditi Singh, Abul Ehtesham, Saket Kumar, and Tala Talaei Khoei. Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG, February 2025. arXiv:2501.09136 [cs]. URL: https://doi.org/10.48550/arXiv.2501.09136.
  15. Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, and Bin Cui. Retrieval-Augmented Generation for AI-Generated Content: A Survey. Data Science and Engineering, January 2026. URL: https://doi.org/10.1007/s41019-025-00335-5.
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact