Dr Leticia Cagnina

My research focuses on building trustworthy intelligent systems whose behavior can be understood, evaluated, and deployed responsibly in real-world environments. Throughout my career, I have combined machine learning, natural language processing, optimization, and intelligent multi-agent systems to address problems where autonomous decision-making must remain transparent, reproducible, and empirically validated. Rather than developing isolated algorithms, my work emphasizes rigorous experimental methodology, reproducible evaluation, and open research infrastructure that enables reliable comparison between competing approaches.