Metraipolis › archive › dc_71eb5901f005

Schema-Agnostic Graph Reasoning Agent for Hybrid Knowledge Graphs — arXiv:2608.15834

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15834
License (as archived): CC0-1.0
Archived: 2026-10-18T17:29:00.622Z
SHA-256 of the archived text: fa556db5e6d3876609c16d5974af049367a47eaf495e7765d4d635e23306e8cf
Stable URL of this page: https://metraipolis.com/documento/dc_71eb5901f005

How to cite

Schema-Agnostic Graph Reasoning Agent for Hybrid Knowledge Graphs — arXiv:2608.15834 — arXiv (en), https://arxiv.org/abs/2608.15834 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71eb5901f005 (Metraipolis archive dc_71eb5901f005, sha256 fa556db5e6d3876609c16d5974af049367a47eaf495e7765d4d635e23306e8cf)

BibTeX

@misc{dc71eb5901f005,
  title = {Schema-Agnostic Graph Reasoning Agent for Hybrid Knowledge Graphs — arXiv:2608.15834},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15834},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71eb5901f005; sha256 fa556db5e6d3876609c16d5974af049367a47eaf495e7765d4d635e23306e8cf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15834. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-calling LLM agents navigate unfamiliar codebases with a handful of generic primitives for listing, reading and searching files (ls, cat, grep). A knowledge graph admits the same interface: listing neighbours, reading node content and searching descriptions are the same operations on a different substrate. Building on this correspondence, we present GRA, a Graph Reasoning Agent that explores hybrid knowledge graphs, whose nodes are either textual concepts or relational tables, with seven generic tools, discovering everything domain-specific at run time. On UFK-M (Unified Factory Knowledge Model), an industrial benchmark of 258 analytical questions whose gold answers are produced by executing validated SQL programs, GRA beats a full-context agent by 5.1 pp (88.4% vs. 83.3%), while reading under a third of its input tokens. A graph-free control shows the gain comes chiefly from selective agentic access rather than graph topology, and that the effect depends on a model able to drive tools reliably. Seeing less, the agent answers better: selective navigation over a structured substrate beats exhaustive context.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.15834 — 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 2026-10-18T16:29:13.835Z 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).