Spell : Synthesis of Programmatic Edits Using LLMs
ACM Transactions on Software Engineering and Methodology · 29.10.2026
DOI: 10.1145/3857915 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 29.10.2026. Verfasst von Daniel Ramos und 5 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben.
Abstract (Originalsprache)
Library migration is a common but error-prone task in software development. Developers may need to replace one library with another due to reasons like changing requirements or licensing changes. Migration typically entails updating and rewriting source code manually. While automated migration tools exist, most rely on mining examples from real-world projects that have already undergone similar migrations. However, these data are scarce, and collecting them for arbitrary pairs of libraries is difficult. Moreover, these migration tools often miss out on leveraging modern code transformation infrastructure. In this paper, we present a new approach to automated API migration that sidesteps the limitations described above. Instead of relying on existing migration data or using LLMs directly for transformation, we use LLMs to extract migration examples. Next, we use an agent to generalize those examples to reusable transformation scripts in PolyglotPiranha, a modern code transformation tool. Our method distills latent migration knowledge from LLMs into structured, testable, and repeatable migration logic, without requiring preexisting corpora or manual engineering effort. Experimental results across Python libraries show that our system can generate diverse migration examples and synthesize transformation scripts that generalize to real-world codebases.
Zitieren
APA
Ramos, D., Gamboa, C., Lynce, I., Manquinho, V., Martins, R., & Goues, C. L. (2026). Spell : Synthesis of Programmatic Edits Using LLMs. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3857915
Vancouver
Ramos D, Gamboa C, Lynce I, Manquinho V, Martins R, Goues CL. Spell : Synthesis of Programmatic Edits Using LLMs. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3857915
BibTeX
@article{Ramos2026,
author = {Ramos, Daniel and Gamboa, Catarina and Lynce, Inês and Manquinho, Vasco and Martins, Ruben and Goues, Claire Le},
title = {Spell : Synthesis of Programmatic Edits Using LLMs},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
doi = {10.1145/3857915}
}
EUVIMED