Evaluating Neuro-Symbolic AI Architectures: Design Principles, Qualitative Benchmark, Comparative Analysis and Results

Oualid BOUGZIME, Samir Jabbar, Christophe Cruz, Frédéric Demoly
Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, PMLR 284:1119-1143, 2025.

Abstract

Neuro-symbolic artificial intelligence (NSAI) represents a transformative approach in artificial intelligence (AI) by combining deep learning’s ability to handle large-scale and unstructured data with the structured reasoning of symbolic methods. By leveraging their complementary strengths, NSAI enhances generalization, reasoning, and scalability while addressing key challenges such as transparency and data efficiency. This paper systematically studies diverse NSAI architectures, highlighting their unique approaches to integrating neural and symbolic components. This study then evaluates these architectures against comprehensive set of criteria, including generalization, reasoning capabilities, transferability, and interpretability, therefore providing a comparative analysis of their respective strengths and limitations. Notably, the Neuro $\rightarrow$ Symbolic $\leftarrow$ Neuro model consistenty outperforms its counterparts across all evaluation metrics. This result aligns with state-of-the-art research that highlight the efficacy of such architectures in harnessing advanced technologies like multi-agent systems. Moreover, our NSAI framework using retrieval-augmented illustrates how the 4D printing ontology can be systematically enriched with additional classes, object properties, data properties and individuals.

Cite this Paper

BibTeX
@InProceedings{pmlr-v284-bougzime25a, title = {Evaluating Neuro-Symbolic AI Architectures: Design Principles, Qualitative Benchmark, Comparative Analysis and Results}, author = {BOUGZIME, Oualid and Jabbar, Samir and Cruz, Christophe and Demoly, Fr\'{e}d\'{e}ric}, booktitle = {Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning}, pages = {1119--1143}, year = {2025}, editor = {H. Gilpin, Leilani and Giunchiglia, Eleonora and Hitzler, Pascal and van Krieken, Emile}, volume = {284}, series = {Proceedings of Machine Learning Research}, month = {08--10 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v284/main/assets/bougzime25a/bougzime25a.pdf}, url = {https://proceedings.mlr.press/v284/bougzime25a.html}, abstract = {Neuro-symbolic artificial intelligence (NSAI) represents a transformative approach in artificial intelligence (AI) by combining deep learning’s ability to handle large-scale and unstructured data with the structured reasoning of symbolic methods. By leveraging their complementary strengths, NSAI enhances generalization, reasoning, and scalability while addressing key challenges such as transparency and data efficiency. This paper systematically studies diverse NSAI architectures, highlighting their unique approaches to integrating neural and symbolic components. This study then evaluates these architectures against comprehensive set of criteria, including generalization, reasoning capabilities, transferability, and interpretability, therefore providing a comparative analysis of their respective strengths and limitations. Notably, the Neuro $\rightarrow$ Symbolic $\leftarrow$ Neuro model consistenty outperforms its counterparts across all evaluation metrics. This result aligns with state-of-the-art research that highlight the efficacy of such architectures in harnessing advanced technologies like multi-agent systems. Moreover, our NSAI framework using retrieval-augmented illustrates how the 4D printing ontology can be systematically enriched with additional classes, object properties, data properties and individuals.} }
Endnote
%0 Conference Paper %T Evaluating Neuro-Symbolic AI Architectures: Design Principles, Qualitative Benchmark, Comparative Analysis and Results %A Oualid BOUGZIME %A Samir Jabbar %A Christophe Cruz %A Frédéric Demoly %B Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Leilani H. Gilpin %E Eleonora Giunchiglia %E Pascal Hitzler %E Emile van Krieken %F pmlr-v284-bougzime25a %I PMLR %P 1119--1143 %U https://proceedings.mlr.press/v284/bougzime25a.html %V 284 %X Neuro-symbolic artificial intelligence (NSAI) represents a transformative approach in artificial intelligence (AI) by combining deep learning’s ability to handle large-scale and unstructured data with the structured reasoning of symbolic methods. By leveraging their complementary strengths, NSAI enhances generalization, reasoning, and scalability while addressing key challenges such as transparency and data efficiency. This paper systematically studies diverse NSAI architectures, highlighting their unique approaches to integrating neural and symbolic components. This study then evaluates these architectures against comprehensive set of criteria, including generalization, reasoning capabilities, transferability, and interpretability, therefore providing a comparative analysis of their respective strengths and limitations. Notably, the Neuro $\rightarrow$ Symbolic $\leftarrow$ Neuro model consistenty outperforms its counterparts across all evaluation metrics. This result aligns with state-of-the-art research that highlight the efficacy of such architectures in harnessing advanced technologies like multi-agent systems. Moreover, our NSAI framework using retrieval-augmented illustrates how the 4D printing ontology can be systematically enriched with additional classes, object properties, data properties and individuals.
APA
BOUGZIME, O., Jabbar, S., Cruz, C. & Demoly, F.. (2025). Evaluating Neuro-Symbolic AI Architectures: Design Principles, Qualitative Benchmark, Comparative Analysis and Results. Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, in Proceedings of Machine Learning Research 284:1119-1143 Available from https://proceedings.mlr.press/v284/bougzime25a.html.

Related Material