NeuroSynt: A Neuro-symbolic Portfolio Solver for Reactive Synthesis

TL;DR

NeuroSynt is a novel neuro-symbolic framework that combines neural networks and symbolic model checkers to improve reactive synthesis, verified for correctness and demonstrated to outperform existing solvers on challenging benchmarks.

Contribution

It introduces NeuroSynt, a flexible, open-source neuro-symbolic framework that enhances reactive synthesis by integrating neural models with symbolic verification.

Findings

NeuroSynt effectively handles challenging specifications.

It improves performance over existing reactive synthesis solvers.

The framework contributes novel solutions to SYNTCOMP benchmarks.

Abstract

We introduce NeuroSynt, a neuro-symbolic portfolio solver framework for reactive synthesis. At the core of the solver lies a seamless integration of neural and symbolic approaches to solving the reactive synthesis problem. To ensure soundness, the neural engine is coupled with model checkers verifying the predictions of the underlying neural models. The open-source implementation of NeuroSynt provides an integration framework for reactive synthesis in which new neural and state-of-the-art symbolic approaches can be seamlessly integrated. Extensive experiments demonstrate its efficacy in handling challenging specifications, enhancing the state-of-the-art reactive synthesis solvers, with NeuroSynt contributing novel solves in the current SYNTCOMP benchmarks.