Théo Matricon — accepted AI-conference papers

2025

Eco Search: A No-delay Best-First Search Algorithm for Program Synthesis

Théo Matricon, Nathanaël Fijalkow, Guillaume Lagarde

AAAI 2025technical

Many approaches to program synthesis perform a combinatorial search within a large space of programs to find one that satisfies a given specification. To tame the search space blowup, previous works introduced probabilistic and neural approaches to guide this combinatorial search by inducing heurist…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Scaling Neural Program Synthesis with Distribution-Based Search

Nathanaël Fijalkow, Guillaume Lagarde, Théo Matricon, Kevin Ellis, Pierre Ohlmann, Akarsh Nayan Potta

AAAI 2022technical

We consider the problem of automatically constructing computer programs from input-output examples. We investigate how to augment probabilistic and neural program synthesis methods with new search algorithms, proposing a framework called distribution-based search. Within this framework, we introduce…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗