Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
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.
Related
- Stable large-scale network architecture and structured individual variability in the awake mouse brain
- MedEvo: Medical Reasoning Evolution through Knowledge Navigation
- CircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathies
- From structured knowledge to flexible behaviour: the importance of local prefrontal computations
- Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV
BibTeX
@misc{jia2026neural,
title = {{Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge}},
author = {Zixing Jia and Yuhang Pan and Ni Ji},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36620},
eprint = {2609.36620},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36620},
}
RIS
TY - UNPB
TI - Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
AU - Zixing Jia
AU - Yuhang Pan
AU - Ni Ji
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.36620
UR - https://arxiv.org/abs/2609.36620
AB - 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.
ER -