Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking
IEEE Transactions on Services Computing · 2026-03 · 19 (2) · 1520-1534
DOI: 10.1109/tsc.2026.3665441 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2026-03. Verfasst von Robin D. Pesl und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: German Federal Ministry for Economic Affairs and Climate Action, State of Baden-Württemberg, GSaME.
Abstract (Originalsprache)
Integrating multiple (sub-)systems is essential to create advanced Information Systems. Difficulties mainly arise when integrating dynamic environments, e.g., the integration at design time of not yet existing services. This has been traditionally addressed using a registry that provides the API documentation of the endpoints. Large language models (LLMs) have been shown to be capable of automatically creating system integrations (e.g., as service composition) based on this documentation but require concise input due to input token limitations, especially regarding comprehensive API descriptions. Currently, it is unknown how best to preprocess these API descriptions. In the present work, we (i) analyze the usage of Retrieval Augmented Generation (RAG) for endpoint discovery and the chunking, i.e., preprocessing, of state-of-practice OpenAPIs to reduce the input token length while preserving the most relevant information. To further reduce the input token length for the composition prompt and improve endpoint retrieval, we propose (ii) a Discovery Agent that only receives a summary of the most relevant endpoints and retrieves specification details on demand. We evaluate RAG for endpoint discovery using (iii) a proposed novel service discovery benchmark SOCBench-D representing a general setting across numerous domains and the real-world RestBench benchmark, first, for the different chunking possibilities and parameters measuring the endpoint retrieval accuracy. Then, we assess the Discovery Agent using the same test data set. The prototype shows how to successfully employ RAG for endpoint discovery to reduce the token count. Our experiments show that endpoint-based approaches outperform naïve chunking methods for preprocessing. Relying on an agent significantly improves precision while being prone to decrease recall, disclosing the need for further reasoning capabilities.
Förderung
- German Federal Ministry for Economic Affairs and Climate Action
- State of Baden-Württemberg
- GSaME
Zitieren
APA
Pesl, R. D., Mathew, J. G., Mecella, M., & Aiello, M. (2026). Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking. IEEE Transactions on Services Computing, 19(2), 1520-1534. https://doi.org/10.1109/tsc.2026.3665441
Vancouver
Pesl RD, Mathew JG, Mecella M, Aiello M. Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking. IEEE Transactions on Services Computing. 2026;19(2):1520-1534. doi:10.1109/tsc.2026.3665441
BibTeX
@article{Pesl2026,
author = {Pesl, Robin D. and Mathew, Jerin G. and Mecella, Massimo and Aiello, Marco},
title = {Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking},
journal = {IEEE Transactions on Services Computing},
year = {2026},
volume = {19},
number = {2},
pages = {1520--1534},
doi = {10.1109/tsc.2026.3665441}
}
EUVIMED