Metraipolis › archive › dc_e3bf0942dfdc

Better Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference — arXiv:2610.30611

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30611
License (as archived)
CC0-1.0
Archived
2026-10-23T15:12:55.816Z
SHA-256 of the archived text
a7375aff28d82e8b15345c18f154acccb0632d5b54133fed3b6ad62638a7ef56
Stable URL of this page
https://metraipolis.com/documento/dc_e3bf0942dfdc

How to cite

Better Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference — arXiv:2610.30611 — arXiv (en), https://arxiv.org/abs/2610.30611 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3bf0942dfdc (Metraipolis archive dc_e3bf0942dfdc, sha256 a7375aff28d82e8b15345c18f154acccb0632d5b54133fed3b6ad62638a7ef56)
BibTeX
@misc{dce3bf0942dfdc,
  title = {Better Reasoning, Not Just Bigger Models: A Structure-Grounded Framework for Efficient and Reliable Inference — arXiv:2610.30611},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30611},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3bf0942dfdc; sha256 a7375aff28d82e8b15345c18f154acccb0632d5b54133fed3b6ad62638a7ef56},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30611. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scaling large language models has substantially improved linguistic fluency, yet reliable autonomous agents require more than fluent generation. In multi-turn inference, current agentic systems often produce semantically plausible but structurally ungrounded reasoning, especially under incomplete observations. We propose Structure-Grounded Uncertainty Reduction (SGUR), a training-free framework that complements token-level generation with active uncertainty reduction over structured hypothesis spaces. SGUR represents incomplete observations as a query graph and aligns them with candidate hypothesis graphs through a prior-weighted partial graph matching mechanism, where database-derived empirical priors assign greater importance to decision-relevant relations rather than treating all graph edges uniformly. The resulting inference state is iteratively refined by an active information-gain strategy that selects the next most informative node to query, systematically pruning the candidate space. We instantiate SGUR on a challenging PrimeKG-derived sequential medical diagnosis benchmark, demonstrating that structural grounding can partially substitute for model scale: starting from only two observed symptoms, SGUR achieves 92.5% Hit@3, outperforming the strongest Graph-RAG baseline by 9.4 percentage points while using approximately 5x fewer tokens. Notably, SGUR enables smaller backbone models to match or exceed the performance of models up to 10x larger, suggesting that structural grounding provides a more robust and efficient paradigm for scaling agent performance than relying exclusively on increasing model size.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.30611 — 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 2026-10-23T15:09:08.377Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).