Search Swarm: Multiagent Large Language Models Framework for E-commerce Product Search

Isyanbaev, Nagim; Makarov, Ilya

doi:10.24963/ijcai.2025/1263

Search Swarm: Multiagent Large Language Models Framework for E-commerce Product Search

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Demo Track. Pages 11062-11066.

https://doi.org/10.24963/ijcai.2025/1263

Keywords

Agent-based and Multi-agent Systems: MAS: Agent theories and models
Agent-based and Multi-agent Systems: MAS: Applications
Agent-based and Multi-agent Systems: MAS: Coordination and cooperation
Agent-based and Multi-agent Systems: MAS: Engineering methods, platforms, languages and tools

Abstract

Search engines are vital for online e-commerce but often struggle with long, detailed queries. We introduce Search Swarm, a novel multi-agent system designed to improve search engine navigation on platforms like Amazon by accurately locating relevant products based on user instructions. Search Swarm employs multiple large language model (LLM) agents, each with a specific role: query planner, searcher, critic, and attribute selector. These agents collaborate to generate search queries, evaluate results, and identify the best product options tailored to users' needs. Our framework outperforms existing methods like ReAct and Reflexion in the WebShop environment, achieving a reward score of 62.64, compared to scores of 54.1, 59.8, 61.5, and 58.2 for other approaches. Furthermore, in a comparison with a basic rule-based method on Amazon, Search Swarm achieved a score 38.71 points higher and a 41\% greater success rate, demonstrating its superior ability to provide relevant product matches over traditional search engines.

Nagim Isyanbaev, and Ilya Makarov. 2025. Search Swarm: Multiagent Large Language Models Framework for E-commerce Product Search. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 11062–11066. https://doi.org/10.24963/ijcai.2025/1263

@inproceedings{ijcai2025p1263,
  title     = {Search Swarm: Multiagent Large Language Models Framework for E-commerce Product Search},
  author    = {Isyanbaev, Nagim and Makarov, Ilya},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {11062--11066},
  year      = {2025},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2025/1263},
  url       = {https://doi.org/10.24963/ijcai.2025/1263},
}

TY  - CPAPER
TI  - Search Swarm: Multiagent Large Language Models Framework for E-commerce Product Search
AU  - Isyanbaev, Nagim
AU  - Makarov, Ilya
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 11062
EP  - 11066
DO  - 10.24963/ijcai.2025/1263
UR  - https://doi.org/10.24963/ijcai.2025/1263
ER  -