EUVIMEDEUVIMED entdecken
Crossref

Interactive Web API Recommendation via LLM‐Enhanced Semantics and Multi‐Round Reward Feedback

Guosheng Kang, Zhuo Chen, Jianxun Liu, Yang Wang, Pei Li, Min Shi

Concurrency and Computation: Practice and Experience · 2026-04 · 38 (8)

DOI: 10.1002/cpe.70704 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 16.04.2026. Verfasst von Guosheng Kang und 5 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the explosive growth in the number of Web APIs, selecting an appropriate combination of APIs from massive services for mashup development has become an extremely challenging task. Existing research on API recommendation is mostly limited to a one‐shot, static recommendation mode, which struggles to accurately capture developers' vague requirement intentions and lacks an interactive mechanism to capture users' dynamic feedback. To this end, this paper proposes a novel interactive Web API recommendation framework named iLLMRec. First, the framework leverages a Large Language Model (LLM) to perform semantic enhancement on raw requirements, improving the clarity and completeness of descriptions. Subsequently, a feature extraction module is constructed by combining GloVe, CNN, and the self‐attention mechanism to deeply fuse the complex semantic correlations between requirements and APIs. To realize the dynamic optimization of recommendations, we innovatively introduce an interactive mechanism based on multi‐round reward feedback, and further transform API and category recommendations into a multi‐label classification problem. With the Binary Cross‐Entropy Loss (BCELoss) as the core loss function, the model parameters are adjusted in real time according to developers' selection behaviors. Experimental results on the real ProgrammableWeb dataset show that iLLMRec significantly outperforms existing state‐of‐the‐art methods in core metrics such as Precision, Recall, F1‐score, and NDCG. Experiments demonstrate that the combination of LLM‐based semantic enhancement and interactive feedback can effectively improve the accuracy of Web API recommendations, providing efficient decision support for complex mashup development.

Zitieren

APA

Kang, G., Chen, Z., Liu, J., Wang, Y., Li, P., & Shi, M. (2026). Interactive Web API Recommendation via LLM‐Enhanced Semantics and Multi‐Round Reward Feedback. Concurrency and Computation: Practice and Experience, 38(8). https://doi.org/10.1002/cpe.70704

Vancouver

Kang G, Chen Z, Liu J, Wang Y, Li P, Shi M. Interactive Web API Recommendation via LLM‐Enhanced Semantics and Multi‐Round Reward Feedback. Concurrency and Computation: Practice and Experience. 2026;38(8). doi:10.1002/cpe.70704

BibTeX
@article{Kang2026,
  author = {Kang, Guosheng and Chen, Zhuo and Liu, Jianxun and Wang, Yang and Li, Pei and Shi, Min},
  title = {Interactive Web API Recommendation via LLM‐Enhanced Semantics and Multi‐Round Reward Feedback},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2026},
  volume = {38},
  number = {8},
  doi = {10.1002/cpe.70704}
}
Kostenlos starten →