Scholarlink

<p>Large-scale neural architectures exhibit systematic failures in compositional generalization and formal verifiability despite remarkable pattern recognition capabilities. This paper introduces the Neural-Symbolic-Verification (NSV) Loop–a functional decomposition framework–and uses it to systematically survey neuro-symbolic integration as a principled pathway toward artificial general intelligence. The NSV Loop organizes hybrid architectures through four computational stages structuring perception, symbolic execution, verification, and feedback. We operationalize the Grounding-Instructibility-Alignment (G-I-A) framework for production assessment and demonstrate quantifiable advantages: perfect compositional accuracy on SCAN (100% vs 13.8% neural baseline, length split), sample efficiency gains exceeding 10<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>×</mo> </math></EquationSource> </InlineEquation> on visual reasoning tasks, and formal verification achieving certification rates above 95% with sub-100ms latency in autonomous systems. Analysis documents critical bottlenecks–grounding complexity scaling exponentially with entity count, cross-domain transfer exhibiting near-zero retention, and adversarial robustness evaluation remaining absent. The NSV+G-I-A framework enables systematic comparison manifesting when hybrid integration justifies complexity: safety-critical applications requiring formal guarantees, data-scarce environments, and compositional reasoning tasks. We establish clear capability boundaries distinguishing reliable improvements from speculative claims while proposing testable research directions with explicit validation protocols.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Neuro-Symbolic pathways to AGI: compositional reasoning and trustworthy deployment

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月10日

查看全文
  • Safayat Bin Hakim,
  • Kanchon Gharami,
  • Huihui Wang,
  • Muhammad Adil,
  • Alvaro Velasquez,
  • Houbing Herbert Song

摘要

Large-scale neural architectures exhibit systematic failures in compositional generalization and formal verifiability despite remarkable pattern recognition capabilities. This paper introduces the Neural-Symbolic-Verification (NSV) Loop–a functional decomposition framework–and uses it to systematically survey neuro-symbolic integration as a principled pathway toward artificial general intelligence. The NSV Loop organizes hybrid architectures through four computational stages structuring perception, symbolic execution, verification, and feedback. We operationalize the Grounding-Instructibility-Alignment (G-I-A) framework for production assessment and demonstrate quantifiable advantages: perfect compositional accuracy on SCAN (100% vs 13.8% neural baseline, length split), sample efficiency gains exceeding 10 \(\times \) × on visual reasoning tasks, and formal verification achieving certification rates above 95% with sub-100ms latency in autonomous systems. Analysis documents critical bottlenecks–grounding complexity scaling exponentially with entity count, cross-domain transfer exhibiting near-zero retention, and adversarial robustness evaluation remaining absent. The NSV+G-I-A framework enables systematic comparison manifesting when hybrid integration justifies complexity: safety-critical applications requiring formal guarantees, data-scarce environments, and compositional reasoning tasks. We establish clear capability boundaries distinguishing reliable improvements from speculative claims while proposing testable research directions with explicit validation protocols.