Commit0: Library Generation from Scratch

Gorde:

Xehetasun bibliografikoak
Argitaratua izan da:	arXiv.org (Dec 2, 2024), p. n/a
Egile nagusia:	Zhao, Wenting
Beste egile batzuk:	Jiang, Nan, Lee, Celine, Chiu, Justin T, Cardie, Claire, Gallé, Matthias, Rush, Alexander M
Argitaratua:	Cornell University Library, arXiv.org
Gaiak:	Application programming interface Static code analysis Feedback Specifications Software development Benchmarks Speech recognition
Sarrera elektronikoa:	Citation/Abstract Full text outside of ProQuest
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!

Deskribapena
Laburpena:	With the goal of benchmarking generative systems beyond expert software development ability, we introduce Commit0, a benchmark that challenges AI agents to write libraries from scratch. Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests, with the goal of producing an implementation of this API accordingly. The implementation is validated through running these unit tests. As a benchmark, Commit0 is designed to move beyond static one-shot code generation towards agents that must process long-form natural language specifications, adapt to multi-stage feedback, and generate code with complex dependencies. Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate. Our experiments demonstrate that while current agents can pass some unit tests, none can yet fully reproduce full libraries. Results also show that interactive feedback is quite useful for models to generate code that passes more unit tests, validating the benchmarks that facilitate its use.
ISSN:	2331-8422
Baliabidea:	Engineering Database