Metraipolis › archive › dc_32fb0ae2f638

Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery — arXiv:2608.15919

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15919
License (as archived)
CC0-1.0
Archived
2026-10-18T18:04:46.211Z
SHA-256 of the archived text
9b0332a3813ac9fbbf407bc8e3d586f440a0f741e4b44a3679080abaef0ea620
Stable URL of this page
https://metraipolis.com/documento/dc_32fb0ae2f638

How to cite

Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery — arXiv:2608.15919 — arXiv (en), https://arxiv.org/abs/2608.15919 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_32fb0ae2f638 (Metraipolis archive dc_32fb0ae2f638, sha256 9b0332a3813ac9fbbf407bc8e3d586f440a0f741e4b44a3679080abaef0ea620)
BibTeX
@misc{dc32fb0ae2f638,
  title = {Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery — arXiv:2608.15919},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15919},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_32fb0ae2f638; sha256 9b0332a3813ac9fbbf407bc8e3d586f440a0f741e4b44a3679080abaef0ea620},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15919. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15919 — 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 2026-10-18T16:29:14.061Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).