Metraipolis › archive › dc_c07e89478198

GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving — arXiv:2610.12391

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12391
License (as archived)
CC0-1.0
Archived
2026-10-09T05:50:51.157Z
SHA-256 of the archived text
a74ceb5c65beca870b678d564764bd97cc24236e2239711a05b1da62fbb65e23
Stable URL of this page
https://metraipolis.com/documento/dc_c07e89478198

How to cite

GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving — arXiv:2610.12391 — arXiv (en), https://arxiv.org/abs/2610.12391 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c07e89478198 (Metraipolis archive dc_c07e89478198, sha256 a74ceb5c65beca870b678d564764bd97cc24236e2239711a05b1da62fbb65e23)
BibTeX
@misc{dcc07e89478198,
  title = {GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving — arXiv:2610.12391},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12391},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c07e89478198; sha256 a74ceb5c65beca870b678d564764bd97cc24236e2239711a05b1da62fbb65e23},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12391. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric entities, relations, and constraints into explicit textual representations for the model to reason over. However, effective formalization is highly non-trivial: on Geometry3K, structure injection fixes 28 errors but introduces 13 new ones among 200 examples. Redundant relations can distract the model, while ambiguous references to diagram elements can lead it to apply constraints incorrectly. This suggests that the key challenge is not merely extracting more geometric facts, but organizing them into representations that support downstream reasoning. To fully exploit the power of formalization, we further propose GeoReform, a reflective formalization evolution framework that treats formalization as an optimizable policy rather than a fixed parser output. GeoReform executes the full reasoning pipeline, collects failed rollouts, diagnoses defects in the current representation, and mutates the policy to better select, ground, group, and present geometric entities, relations, constraints, and targets. On Geometry3K, GeoReform improves Qwen3VL-2B accuracy from 42.0\% to 56.0\%. Extensive experiments and analyses across geometry reasoning benchmarks demonstrate that effective formalization is crucial for improving multimodal geometry reasoning.

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/2610.12391 — 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 2026-10-09T05:47:01.118Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).