{
  "abstract": "Structural reasoning, the ability to recognize and make inferences over the relational structure between objects and concepts, is a hallmark of human cognition, yet prevailing methods often collapse relational topology into flat embeddings, cannot discover hidden structure and lack interpretability. We introduce Neural Structural Reasoner (NSR), a brain-inspired network that preserves relational structure directly in the connectivity and dynamics of coupled neuronal populations. NSR draws inspiration from three biological mechanisms: multi-layered architecture for encoding hierarchical knowledge, stable representations of entity and concepts, and path integration for input-driven state inference. At query time, NSR parallelizes computation over candidate relational structures and leverages confidence-weighted scores to perform link prediction. Across standard knowledge-graph benchmarks, NSR achieves competitive accuracy without leading on every dataset, and has lower reported training times than several neural baselines. Because reasoning is implemented through sequences of human-readable neuron activations, NSR affords native interpretability by tracking intermediate inference steps. The model further extracts latent relational hierarchies and compositional rules, demonstrating the brain-inspired architecture as an effective, efficient, and highly interpretable substrate for structural reasoning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.36620",
  "author_total": 3,
  "authors": [
    {
      "name": "Zixing Jia"
    },
    {
      "name": "Yuhang Pan"
    },
    {
      "name": "Ni Ji"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bqq0geretpedy.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.36620",
  "fulltext_url": null,
  "id": "bqq0geretpedy",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.36620",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "1702|Advanced Graph Neural Networks"
    ]
  ],
  "openalex": "W7214904022",
  "pdf_url": "https://arxiv.org/pdf/2609.36620",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-29",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bqq0geretpedy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:36Z",
      "native_id": "2609.36620",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.36620"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge",
  "title_text": "Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:36Z",
  "url": "https://research.draconitic.com/paper/bqq0geretpedy",
  "venue": "arXiv",
  "versions": []
}