Emilio Delgado
Making LLM-generated code measurable, testable, and trustworthy through specifications.
About
I'm a PhD student at INTIA (University of Extremadura), focused on making AI-assisted software development more reliable and useful in practice.
My research focuses on quality assurance for code produced by large language models. I use specification-driven development (SDD) to turn formal specifications into tests, checks, and evaluation artifacts that help surface mistakes earlier and make generated code easier to trust.
The broader goal is transparent, reproducible AI-assisted development: models can help us move faster, but we still need systematic ways to measure and improve correctness without losing confidence in the result.
Journey
Research
Education
Focus areas
Publications
Systematic Benchmarking of LLM-based Multi-Agent Systems for Software Engineering
JISBD 2025
AI-Based System for Assistance in Minimally Invasive Renal Procedures
Using Mixed Reality. First Steps