Control Models for In-IDE Code Completion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914285848887296 |
|---|---|
| author | de Moor, Aral Hrynevich, Yana Badzeika, Hleb Furda, Vladyslav Kojic, Marko Savelev, Artem Cvejoski, Kostadin Rovdo, Darya Garanina, Ekaterina |
| author_facet | de Moor, Aral Hrynevich, Yana Badzeika, Hleb Furda, Vladyslav Kojic, Marko Savelev, Artem Cvejoski, Kostadin Rovdo, Darya Garanina, Ekaterina |
| contents | We introduce control models for LLM-powered code completion in JetBrains IDEs: ML classifiers which trigger inference and filter the generated suggestions to better align them with users and reduce unnecessary requests. To this end, we evaluate boosting- and transformer-based architectures on an offline dataset of real code completions with n=98 users. We further evaluate the offline classification performance of our boosting-based approach on a range of syntactically diverse languages; and perform an A/B study in a production environment where they improve completion efficiency and quality metrics. With this study, we hope to demonstrate the potential in using auxiliary models for smarter in-IDE integration of LLM-driven features, highlight fruitful future directions, and open problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20223 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Control Models for In-IDE Code Completion de Moor, Aral Hrynevich, Yana Badzeika, Hleb Furda, Vladyslav Kojic, Marko Savelev, Artem Cvejoski, Kostadin Rovdo, Darya Garanina, Ekaterina Software Engineering We introduce control models for LLM-powered code completion in JetBrains IDEs: ML classifiers which trigger inference and filter the generated suggestions to better align them with users and reduce unnecessary requests. To this end, we evaluate boosting- and transformer-based architectures on an offline dataset of real code completions with n=98 users. We further evaluate the offline classification performance of our boosting-based approach on a range of syntactically diverse languages; and perform an A/B study in a production environment where they improve completion efficiency and quality metrics. With this study, we hope to demonstrate the potential in using auxiliary models for smarter in-IDE integration of LLM-driven features, highlight fruitful future directions, and open problems. |
| title | Control Models for In-IDE Code Completion |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2601.20223 |