Metraipolis › archive › dc_ff7cdf17cac2

Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge — arXiv:2609.36620

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.36620
License (as archived): CC0-1.0
Archived: 2026-10-07T16:22:47.876Z
SHA-256 of the archived text: 6ba2e618394932547f2eca445338a52d2a7a46de22de0d6c2516da80c4eb38a7
Stable URL of this page: https://metraipolis.com/documento/dc_ff7cdf17cac2

How to cite

Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge — arXiv:2609.36620 — arXiv (en), https://arxiv.org/abs/2609.36620 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff7cdf17cac2 (Metraipolis archive dc_ff7cdf17cac2, sha256 6ba2e618394932547f2eca445338a52d2a7a46de22de0d6c2516da80c4eb38a7)

BibTeX

@misc{dcff7cdf17cac2,
  title = {Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge — arXiv:2609.36620},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36620},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff7cdf17cac2; sha256 6ba2e618394932547f2eca445338a52d2a7a46de22de0d6c2516da80c4eb38a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36620. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2609.36620 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.518Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).