Publications

Please find my articles on my Google Scholar profile or on my DBLP profile. This list serves as permanent links to supplementary material such as code.

2025

EcoSearch: A Constant-Delay Best-First Search Algorithm for Program Synthesis

Théo Matricon, Nathanaël Fijalkow, Guillaume Lagarde
Published in AAAI 2025 A* (23% acceptance rate, 17k+ submissions)

DOI Code

2024

Theoretical foundations for programmatic reinforcement learning

Guruprerana Shabadi, Nathanaël Fijalkow, Théo Matricon
Published in under review

DOI

2023

WikiCoder: Learning to Write Knowledge-Powered Code

Théo Matricon, Nathanaël Fijalkow, Gaëtan Margueritte
Published in SPIN (ETAPS)

Project DOI Code

2022

Software: DeepSynth

Théo Matricon, Nathanaël Fijalkow, Guillaume Lagarde, Kevin Ellis
Published in JOSS

Project DOI Code

Scaling Neural Program Synthesis with Distribution-based Search

Nathanaël Fijalkow, Guillaume Lagarde, Théo Matricon, Kevin Ellis, Pierre Ohlmann, Akarsh Potta
Published in AAAI 2022 A* (Oral, ~5% of submissions accepted for oral, 15% acceptance rate, 9k+ submissions)

Project DOI Code Slides

2021

Statistical Comparison of Algorithm Performance Through Instance Selection

Théo Matricon, Marie Anastacio, Nathanaël Fijalkow, Laurent Simon, Holger H. Hoos
Published in CP 2021 A (30% acceptance rate)

DOI Code Talk Slides