Metraipolis › archive › dc_fce85e211799
Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning — arXiv:2611.09414
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09414
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:34:07.563Z
- SHA-256 of the archived text
faf2bfa7c78b3749989536f08f097137e7680ea3ff7501e3831b67bbf1799d00- Stable URL of this page
https://metraipolis.com/documento/dc_fce85e211799
How to cite
Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning — arXiv:2611.09414 — arXiv (en), https://arxiv.org/abs/2611.09414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fce85e211799 (Metraipolis archive dc_fce85e211799, sha256 faf2bfa7c78b3749989536f08f097137e7680ea3ff7501e3831b67bbf1799d00)
BibTeX
@misc{dcfce85e211799,
title = {Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning — arXiv:2611.09414},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09414},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fce85e211799; sha256 faf2bfa7c78b3749989536f08f097137e7680ea3ff7501e3831b67bbf1799d00},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Knowledge Graphs (KGs) and Large Language Models (LLMs) represent two approaches for knowledge representation and reasoning over heterogeneous data. Recent research has explored their integration through Graph Retrieval-Augmented Generation (GraphRAG) systems, which use KGs to provide structured context to LLMs. However, existing GraphRAG approaches treat KGs as homogeneous graphs and rely on textual similarity between the input prompt and the context, rather than using it as a source of deterministic knowledge. This work proposes an agent-based GraphRAG system that introduces a symbolic layer to integrate deterministic reasoning alongside text similarities. This approach is based on the definition of typed centralities for KGs, where centrality measures are computed separately for each specific KG's class. This information is used to construct a symbolic representation that is provided to the LLM as a deterministic source. The proposed system was mathematically validated and evaluated on a real-world POLE (Person, Object, Location, Event) dataset, comparing reasoning and information retrieval with and without the symbolic layer. The results indicate that the our approach leads to responses that are more consistent with the context, improving the generated outputs. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.09414 — 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 2026-11-09T22:30:47.281Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).