EUVIMEDEUVIMED entdecken
Crossref

MARS: A Multi-Agent Collaborative Reasoning Framework for Service Recommendation

Mingyi Liu, Zijie Yin, Congcong Tian, Shuang Yu, Taotao Cai, Zhihui Xu, Zhongjie Wang

IEEE Transactions on Services Computing · 2026-05 · 19 (3) · 2289-2302

DOI: 10.1109/tsc.2026.3676128 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2026-05. Verfasst von Mingyi Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, State Key Laboratory of Nuclear Power Safety Technology and Equipment+Open Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Service recommendation for mashup development faces critical challenges due to the sparse usage history of newly introduced mashups and APIs, as well as the difficulty of inferring genuine API dependencies from mashup compositions, where APIs are often co-used in a noisy and implicit manner. Traditional collaborative filtering, content-based methods, and standalone LLM-based approaches have limitations in jointly addressing these challenges within a unified framework. We propose MARS, a multi-agent collaborative recommendation framework that systematically integrates semantic alignment, structure-aware retrieval, and validation-based recommendation under a constrained candidate space. MARS incorporates multiple algorithmic components to improve different stages of the service recommendation process. Specifically, agent-driven semantic enrichment substantially mitigates cross-representation semantic mismatch between mashups and APIs, reducing the average Jensen–Shannon distance from 0.7333 to 0.6333, while baseline methods exhibit negligible changes. Structure-aware fine-tuning captures API compositional patterns beyond surface-level semantics, and data-driven weight optimization learns the fusion weights in the hybrid retrieval stage, replacing static retrieval parameters with empirically calibrated strategies. Finally, multi-agent collaborative reasoning enhances robustness by combining diverse proposal generation with validation-based selection. Experiments on ProgrammableWeb dataset demonstrate that MARS consistently outperforms representative baselines, achieving 63.31% Recall@5 compared to 58.28% for Native RAG and 43.35% for the best traditional method (ServeNet). The results indicate that MARS provides an effective and extensible framework for improving mashup-oriented service recommendation.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • State Key Laboratory of Nuclear Power Safety Technology and Equipment+Open Fund

Zitieren

APA

Liu, M., Yin, Z., Tian, C., Yu, S., Cai, T., Xu, Z., & Wang, Z. (2026). MARS: A Multi-Agent Collaborative Reasoning Framework for Service Recommendation. IEEE Transactions on Services Computing, 19(3), 2289-2302. https://doi.org/10.1109/tsc.2026.3676128

Vancouver

Liu M, Yin Z, Tian C, Yu S, Cai T, Xu Z, et al. MARS: A Multi-Agent Collaborative Reasoning Framework for Service Recommendation. IEEE Transactions on Services Computing. 2026;19(3):2289-2302. doi:10.1109/tsc.2026.3676128

BibTeX
@article{Liu2026,
  author = {Liu, Mingyi and Yin, Zijie and Tian, Congcong and Yu, Shuang and Cai, Taotao and Xu, Zhihui and Wang, Zhongjie},
  title = {MARS: A Multi-Agent Collaborative Reasoning Framework for Service Recommendation},
  journal = {IEEE Transactions on Services Computing},
  year = {2026},
  volume = {19},
  number = {3},
  pages = {2289--2302},
  doi = {10.1109/tsc.2026.3676128}
}
Kostenlos starten →