Metraipolis › archive › dc_83bd41883e05

GraphDecide: Benchmarking System One Models on Graph Tasks — arXiv:2610.06354

Source
arXiv
Original
https://arxiv.org/abs/2610.06354
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:33.062Z
SHA-256 of the archived text
71b2c19b1b36caf1667cbee414b5d4a64f494f4654bdcc3bc95fd0f9b0513206
Stable URL of this page
https://metraipolis.com/documento/dc_83bd41883e05

How to cite

GraphDecide: Benchmarking System One Models on Graph Tasks — arXiv:2610.06354 — arXiv, https://arxiv.org/abs/2610.06354 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83bd41883e05 (Metraipolis archive dc_83bd41883e05, sha256 71b2c19b1b36caf1667cbee414b5d4a64f494f4654bdcc3bc95fd0f9b0513206)
BibTeX
@misc{dc83bd41883e05,
  title = {GraphDecide: Benchmarking System One Models on Graph Tasks — arXiv:2610.06354},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06354},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83bd41883e05; sha256 71b2c19b1b36caf1667cbee414b5d4a64f494f4654bdcc3bc95fd0f9b0513206},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06354. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly explored for graph understanding and decision-making, while System One models such as Jev select directly from supplied options. However, the capabilities of System One models on graph-related tasks remain unclear. We introduce GraphDecide, a model-independent benchmark that combines structural task profiles, matched graph-text input contrasts and heuristic-proposal controls to diagnose graph decision performance. We evaluate Jev and related choice-based models alongside language-model baselines, covering fourteen model-interface configurations. Jev's results illustrate the benchmark's central distinctions: accurate adjacency recognition does not guarantee broader structural correctness, joint graph-text input does not consistently improve prediction, and feasible construction does not establish high solution quality. Its task contracts, candidate interfaces and scoring rules support comparison across native selectors and language-model adapters. Code and aggregate results are available at this https URL .

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/2610.06354 — 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 2026-10-06T05:24:05.672Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).