PhD candidate at EPFL and Idiap, in collaboration with Honda Research Institute Europe
I work on neuro-symbolic AI for reliable reasoning by coupling neural and language models to symbolic structure that is sound, checkable, and interpretable.
My research focuses on neuro-symbolic AI and its applications to mechanical engineering. Within this broader context, I focus primarily on engineering design, specifically the automated synthesis of mechanisms. Neural-symbolic integration, symbolic reasoning and formal verification, and agentic reasoning are particular areas of expertise.
Martigny, Switzerland
Latest
Jun 2026
Apr 2026
Jan 2026
May 2025
New preprint: “Controlled Agentic Planning & Reasoning for Mechanism Synthesis.”
Selected work
João Pedro Gandarela, Thiago Rios, Stefan Menzel, André Freitas
arXiv preprint
A reflective adversarial Pareto-search protocol decomposes reasoning modes, stress-tests robustness, and maintains explicit rule memory for constrained mechanism design.
João Pedro Gandarela, Thiago Rios, Stefan Menzel, André Freitas
arXiv preprint
A symbolic “lifting” interface lets language models read, compare, and critique a kinematic simulator’s output, refining linkage designs through modular optimisation and carrying across model families.
João Pedro Gandarela, Thiago Rios, Stefan Menzel, André Freitas
arXiv preprint arXiv:2505.17607
An agentic protocol gives each kind of reasoning (proposing, stress-testing, correcting) its own context and treats worst-case robustness as a first-class objective, so a small, frozen language model becomes reliable on mechanism synthesis through organisation rather than scale.
João Pedro Gandarela de Souza, Danilo Carvalho, André Freitas
Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), pp. 23752–23759
An expressivity-graded analysis of how well large language models induce logical theories, mapping precisely where neural models succeed and fail at formal reasoning.
