analiza aiqbench
Noesis advances Graph-RAG by introducing adaptive parallelism and cross-knowledge-base semantic discovery, enabling smaller models to perform complex multi-hop reasoning without relying on massive cloud APIs. The system's key innovations include a bidirectional graph traversal algorithm that preserves long-range causal connections in documents up to 193 pages while achieving significant speedups through domain-aware quantization. This architecture directly addresses critical bottlenecks in retrieval precision and scalability for enterprise deployments, offering a viable path toward robust on-premises AI systems.
Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery
arXiv:2608.15919v1 Announce Type: cross Abstract: Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-specific corpora. However, existing systems face persistent limitations: (1) static chunking fragments long documents, losing cross-section semantic connections; (2) ingestion pipelines do not scale adaptively; and (3) multi-domain deployments require either a monolithic knowledge base that dilutes retrieval precision or manual user routing. We present Noesis, a decoupled Graph-RAG architecture addressing these limitations through four algorithms: (a) Bidirectional Graph Traversal with a Graph-Feedback Context Resolver simulating human reading with degrading memory; (b) an AIMD Concurrency Controller adapted from TCP congestion control, achieving 23x speedup with zero OOM events; (c) Moesis, domain-aware selective quantization for MoE models achieving 6.3x speedup on 12 GB consumer GPUs; and (d) Mesh, cross-KB semantic routing with runtime structural discovery enabling small on-premises models to perform multi-hop cross-domain reasoning. On HotpotQA (1,000 questions), Noesis achieves 59.5 EM / 74.7 F1, surpassing GraphRAG by +27.8 EM while using a 35B on-premises model for graph construction rather than GPT-4o. Source text verification on a 193-page document confirms 90% precision on long-range causal edges inaccessible to chunk-independent extraction.
Abstract:Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-specific corpora. However, existing systems face persistent limitations: (1) static chunking fragments long documents, losing cross-section semantic connections; (2) ingestion pipelines do not scale adaptively; and (3) multi-domain deployments require either a monolithic knowledge base that dilutes retrieval precision or manual user routing. We present Noesis, a decoupled Graph-RAG architecture addressing these limitations through four algorithms: (a) Bidirectional Graph Traversal with a Graph-Feedback Context Resolver simulating human reading with degrading memory; (b) an AIMD Concurrency Controller adapted from TCP congestion control, achieving 23x speedup with zero OOM events; (c) Moesis, domain-aware selective quantization for MoE models achieving 6.3x speedup on 12 GB consumer GPUs; and (d) Mesh, cross-KB semantic routing with runtime structural discovery enabling small on-premises models to perform multi-hop cross-domain reasoning. On HotpotQA (1,000 questions), Noesis achieves 59.5 EM / 74.7 F1, surpassing GraphRAG by +27.8 EM while using a 35B on-premises model for graph construction rather than GPT-4o. Source text verification on a 193-page document confirms 90% precision on long-range causal edges inaccessible to chunk-independent extraction.
14 pages, 6 figures, 4 tables. Patent pending
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
arXiv:2608.15919 [cs.IR]
(or arXiv:2608.15919v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2608.15919 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.5281/zenodo.21874580 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 302 cuvinte
Subiecte conexe
Multi-agent social intelligence with Strands Agents and Amazon Bedrock
AWS · 14 iul. 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · 15 iul. 2026
An Organizational Second Brain: Building an AI That Learns From Experts
Meta Engineering · 2 sept. 2026
AI and Quantum Computing Briefing
livetradingnews.com · 4 aug. 2026