Paper
Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era
Authors
Giovanni Pio Delvecchio, Lorenzo Molfetta, Gianluca Moro
Abstract
The integration of symbolic computing with neural networks has intrigued researchers since the first theorizations of Artificial intelligence (AI). The ability of Neuro-Symbolic (NeSy) methods to infer or exploit behavioral schema has been widely considered as one of the possible proxies for human-level intelligence. However, the limited semantic generalizability and the challenges in declining complex domains with pre-defined patterns and rules hinder their practical implementation in real-world scenarios. The unprecedented results achieved by connectionist systems since the last AI breakthrough in 2017 have raised questions about the competitiveness of NeSy solutions, with particular emphasis on the Natural Language Processing and Computer Vision fields. This survey examines task-specific advancements in the NeSy domain to explore how incorporating symbolic systems can enhance explainability and reasoning capabilities. Our findings are meant to serve as a resource for researchers exploring explainable NeSy methodologies for real-life tasks and applications. Reproducibility details and in-depth comments on each surveyed research work are made available at https://github.com/disi-unibo-nlp/task-oriented-neuro-symbolic.git.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.03177v1</id>\n <title>Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era</title>\n <updated>2026-03-03T17:34:45Z</updated>\n <link href='https://arxiv.org/abs/2603.03177v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.03177v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>The integration of symbolic computing with neural networks has intrigued researchers since the first theorizations of Artificial intelligence (AI). The ability of Neuro-Symbolic (NeSy) methods to infer or exploit behavioral schema has been widely considered as one of the possible proxies for human-level intelligence. However, the limited semantic generalizability and the challenges in declining complex domains with pre-defined patterns and rules hinder their practical implementation in real-world scenarios. The unprecedented results achieved by connectionist systems since the last AI breakthrough in 2017 have raised questions about the competitiveness of NeSy solutions, with particular emphasis on the Natural Language Processing and Computer Vision fields. This survey examines task-specific advancements in the NeSy domain to explore how incorporating symbolic systems can enhance explainability and reasoning capabilities. Our findings are meant to serve as a resource for researchers exploring explainable NeSy methodologies for real-life tasks and applications. Reproducibility details and in-depth comments on each surveyed research work are made available at https://github.com/disi-unibo-nlp/task-oriented-neuro-symbolic.git.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-03T17:34:45Z</published>\n <arxiv:comment>Accepted for publication at IJCAI-25. Please cite the definitive, copyrighted, peer reviewed and edited version of this Article published in IJCAI 25, pp. 4196-4176, 2025. DOI: https://doi.org/10.24963/ijcai.2025/1157</arxiv:comment>\n <arxiv:primary_category term='cs.AI'/>\n <arxiv:journal_ref>Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025, pages 10418-10426</arxiv:journal_ref>\n <author>\n <name>Giovanni Pio Delvecchio</name>\n </author>\n <author>\n <name>Lorenzo Molfetta</name>\n </author>\n <author>\n <name>Gianluca Moro</name>\n </author>\n <arxiv:doi>10.24963/ijcai.2025/1157</arxiv:doi>\n <link href='https://doi.org/10.24963/ijcai.2025/1157' rel='related' title='doi'/>\n </entry>"
}