mlsanityData to 14 Oct 2026

NeuroSynt: A Neuro-symbolic Portfolio Solver for Reactive Synthesis

arXiv 2401.12131 ↗First posted 22 Jan 2024cs.LO cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 31 of its 62 references that are in the map. First posted on arXiv 22 Jan 2024.

Builds on

31 of 62 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 291
  5. 2019Deep Learning for Symbolic Mathematicscited by 270
  6. 2018Learning a SAT Solver from Single-Bit Supervisioncited by 200
  7. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 161
  8. 2023Baldur: Whole-Proof Generation and Repair with Large Language Modelscited by 119
  9. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  10. 2019Guiding High-Performance SAT Solvers with Unsat-Core Predictionscited by 62
  11. 2023nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Modelscited by 60
  12. 2019Graph Representations for Higher-Order Logic and Theorem Provingcited by 55
19 more
  1. 2020Teaching Temporal Logics to Neural Networkscited by 51
  2. 2018GamePad: A Learning Environment for Theorem Provingcited by 48
  3. 2017Deep Network Guided Proof Searchcited by 47
  4. 2019Learning to Reason in Large Theories without Imitationcited by 27
  5. 2022From Spot 2.0 to Spot 2.10: What's New?cited by 22
  6. 2019CLN2INV: Learning Loop Invariants with Continuous Logic Networkscited by 20
  7. 2019HOList: An Environment for Machine Learning of Higher-Order Theorem Provingcited by 19
  8. 2021Neural Circuit Synthesis from Specification Patternscited by 17
  9. 2021Neural Termination Analysiscited by 16
  10. 2023Iterative Circuit Repair Against Formal Specificationscited by 9
  11. 2018BoSy: An Experimentation Framework for Bounded Synthesiscited by 8
  12. 2022The Reactive Synthesis Competition (SYNTCOMP): 2018-2021cited by 8
  13. 2021Scaling Neural Program Synthesis with Distribution-based Searchcited by 6
  14. 2021Generating Symbolic Reasoning Problems with Transformer GANscited by 5
  15. 2016A High-Level LTL Synthesis Format: TLSF v1.1cited by 4
  16. 2023Guessing Winning Policies in LTL Synthesis by Semantic Learningcited by 4
  17. 2019Data Generation for Neural Programming by Examplecited by 3
  18. 2022Acacia-Bonsai: A Modern Implementation of Downset-Based LTL Realizabilitycited by 2
  19. 2016Bounded Cycle Synthesiscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025SemML: Enhancing Automata-Theoretic LTL Synthesis with Machine Learningcited by 6
  2. 2026SemML 2.0: Synthesizing Controllers for LTLcited by 1
  3. 2026Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Modelscited by 0