Metraipolis › archive › dc_7882e973f57e

Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents — arXiv:2610.06650

Source
arXiv
Original
https://arxiv.org/abs/2610.06650
License (as archived)
CC0-1.0
Archived
2026-10-06T05:28:37.831Z
SHA-256 of the archived text
875626f1aadb55e638df3ead36907ec6bf3339bdff7f46a5151bd999c0b26fa0
Stable URL of this page
https://metraipolis.com/documento/dc_7882e973f57e

How to cite

Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents — arXiv:2610.06650 — arXiv, https://arxiv.org/abs/2610.06650 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7882e973f57e (Metraipolis archive dc_7882e973f57e, sha256 875626f1aadb55e638df3ead36907ec6bf3339bdff7f46a5151bd999c0b26fa0)
BibTeX
@misc{dc7882e973f57e,
  title = {Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents — arXiv:2610.06650},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06650},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7882e973f57e; sha256 875626f1aadb55e638df3ead36907ec6bf3339bdff7f46a5151bd999c0b26fa0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06650. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right entities and properties and chains their relations. Language models offer a natural-language alternative but answer largely from memory, which is least reliable for less prominent entities. We study agents that instead answer by exploring the graph, and argue that two obstacles limit them: the lack of training data recording how a solver explores, and interfaces that add large graph results directly to the model's context. We test three hypotheses: that the difficulty of graph search can be controlled through the structure of a question rather than only through obscure entities or wording; that much of the failure on long-horizon search comes from how retrieved evidence is managed rather than from the model itself; and that, in a suitable environment, open-weight models can match commercial closed ones. We construct multi-hop questions on a frozen Wikidata snapshot by replacing named entities with nested conditions, checking after each expansion that the target remains unique and that every new condition is necessary. We release 10,235 solving traces over single-entity and multi-hop questions, together with the recursive language model (RLM) harness that produced them, in which models batch graph calls, keep results in persistent Python state and interpret selected evidence through sub-calls. On 100 questions, the harness improves both models we ran under both interfaces compared with direct tool calling over the same functions: gpt-6-luna rises from 49 to 61 correct answers, doubling its multi-hop accuracy, and Qwen3.8-27B, an open-weight model served on a single GPU, from 60 to 74.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.06650 — 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 2026-10-06T05:24:20.385Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).