Automatic Code Generation
A lecture I gave at the international colloquium: "AI meets Software Quality."
Abstract:
In this talk, I will present three different works on automatic code generation.
"Evolving Assembly Code in an Adversarial Environment" (https://arxiv.org/abs/2403.19489):
The study evolves assembly code for the CodeGuru competition, aiming to create a survivor program that runs longest in shared memory. Evolved programs discover weaknesses in opponent programs and exploit them.
"From Requirements to Source Code: Evolution of Behavioral Programs" (https://doi.org/10.3390/app12031587):
Genetic programming (GP) combined with behavioral programming (BP) is explored. BP models programs as sets of behavioral threads aligned with system requirements, facilitating effective program generation using GP.
"From Requirements to Source Code for Real: " (ongoing work):
Large language models (LLMs) vastly improved automated code generation, though they struggle with complex behavior, especially involving cross-cutting aspects. Bridging the gap between system requirements and code requires an intermediate design phase. advocates for utilizing LLMs to translate requirements into behavioral programming (BP) specifications. This approach facilitates direct alignment between requirements and BP modules, enabling the generation of cohesive behavior that is aligned with all requirements and eliminating the need for a separate design phase.
En esta página del sitio puede ver el video en línea Automatic Code Generation de Duración hora minuto segunda en buena calidad , que subió el usuario Achiya Elyasaf 10 abril 2024, comparta el enlace con amigos y conocidos, en youtube este video ya ha sido visto 125 veces y le gustó 1 a los espectadores. Disfruta viendo!
