DeepLog: A Software Framework for Modular Neurosymbolic AI

Manhaeve, Robin; Colamonaco, Stefano; Derkinderen, Vincent; Adriaensen, Rik; Van Praet, Lucas; de Raedt, Luc; Marra, Giuseppe

doi:10.24963/ijcai.2026/980

DeepLog: A Software Framework for Modular Neurosymbolic AI

Robin Manhaeve, Stefano Colamonaco, Vincent Derkinderen, Rik Adriaensen, Lucas Van Praet, Luc De Raedt, Giuseppe Marra

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8462-8465.

https://doi.org/10.24963/ijcai.2026/980

Keywords

AI: Uncertainty in AI
AI: Machine Learning
AI: Knowledge Representation and Reasoning

Abstract

DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic systems focus on a particular paradigm and semantics, DeepLog serves as a universal backend that can emulate many systems in the neurosymbolic alphabet soup. By treating diverse neurosymbolic languages as high-level specifications, the DeepLog software automatically compiles them into optimized arithmetic circuits. This design lowers the barrier for machine learning practitioners by treating logic as composable modules, while providing neurosymbolic developers with a shared, high-performance basis for prototyping new integration strategies. The code is available here: https://github.com/ML-KULeuven/deeplog

Robin Manhaeve, Stefano Colamonaco, Vincent Derkinderen, Rik Adriaensen, Lucas Van Praet, Luc de Raedt, and Giuseppe Marra. 2026. DeepLog: A Software Framework for Modular Neurosymbolic AI. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8462–8465. https://doi.org/10.24963/ijcai.2026/980

@inproceedings{ijcai2026p980,
  title     = {DeepLog: A Software Framework for Modular Neurosymbolic AI},
  author    = {Manhaeve, Robin and Colamonaco, Stefano and Derkinderen, Vincent and Adriaensen, Rik and Van Praet, Lucas and de Raedt, Luc and Marra, Giuseppe},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8462--8465},
  year      = {2026},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2026/980},
  url       = {https://doi.org/10.24963/ijcai.2026/980},
}

TY  - CPAPER
TI  - DeepLog: A Software Framework for Modular Neurosymbolic AI
AU  - Manhaeve, Robin
AU  - Colamonaco, Stefano
AU  - Derkinderen, Vincent
AU  - Adriaensen, Rik
AU  - Van Praet, Lucas
AU  - de Raedt, Luc
AU  - Marra, Giuseppe
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8462
EP  - 8465
DO  - 10.24963/ijcai.2026/980
UR  - https://doi.org/10.24963/ijcai.2026/980
ER  -