Neural-Symbolic Dual-Indexing Architectures for Scalable Retrieval-Augmented Generation

Abstract

Contemporary retrieval-augmented generation systems face a fundamental trade-off between semantic comprehensiveness and computational tractability when scaling to billion-token corpora. We present a unified framework that reconciles this tension through neural-symbolic dual-indexing, wherein sparse graph skeletons constructed from high-centrality document chunks enable structured reasoning, while complementary bipartite keyword indices ensure broad semantic coverage. Our architecture achieves this decomposition by formulating retrieval as a constrained optimization problem over heterogeneous index structures, employing Prize-Collecting Steiner Trees for subgraph extraction and Personalized PageRank for multi-hop traversal. Through synergistic integration of Graph Neural Networks with vector embeddings, the system performs explicit relational reasoning while maintaining sub-second query latency. Empirical evaluation across 6.0 benchmark datasets demonstrates that selective skeleton construction from the top 20.0% of chunks—identified via eigenvector centrality on k-nearest neighbor graphs—yields 10.0\times cost reduction relative to exhaustive knowledge graph construction while improving generation quality by 32.4% and retrieval coverage by 92.4%. Furthermore, neural-symbolic coupling enables 7.0-billion parameter models to match GPT-4 performance on multi-hop question answering through single-step graph-guided inference, eliminating iterative retrieval overhead. Production deployments validate sub-200.0ms latency at scale through hierarchical caching strategies that reduce time-to-first-token by 4.0\times. The proposed framework establishes dual-indexing as the canonical architecture for enterprise retrieval systems, providing a principled methodology for balancing semantic understanding against structured reasoning in large-scale information access.