Metraipolis › archive › dc_aa1b498805df

LOCI: A Locator-Critic with Refinement Loop — arXiv:2608.30959

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30959
License (as archived)
CC0-1.0
Archived
2026-10-17T07:55:10.090Z
SHA-256 of the archived text
b223376802c98fca332975b2c17c89418ba1253999cc67467a7f3c911fa03c10
Stable URL of this page
https://metraipolis.com/documento/dc_aa1b498805df

How to cite

LOCI: A Locator-Critic with Refinement Loop — arXiv:2608.30959 — arXiv (en), https://arxiv.org/abs/2608.30959 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa1b498805df (Metraipolis archive dc_aa1b498805df, sha256 b223376802c98fca332975b2c17c89418ba1253999cc67467a7f3c911fa03c10)
BibTeX
@misc{dcaa1b498805df,
  title = {LOCI: A Locator-Critic with Refinement Loop — arXiv:2608.30959},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30959},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa1b498805df; sha256 b223376802c98fca332975b2c17c89418ba1253999cc67467a7f3c911fa03c10},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30959. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language Models (VLMs) still struggle on tasks requiring complex visual understanding. We argue that the core issue is not high-level reasoning, but instead failing to locate critical details in the image. Due to this shortcoming, VLMs generate often plausible but incorrect reasoning based on flawed perceptual grounding. To address this, we propose Locator-Critic (LOCI), a training-free framework that decouples visual search from evidence verification. LOCI employs a Locator agent to propose candidate visual evidence and a separate Critic agent to evaluate its relevance and sufficiency. These agents engage in an iterative refinement loop, progressively improving the evidence until it is adequate to answer the given question. This decoupled, self-correcting process yields substantial performance gains, achieving state-of-the-art results on multiple complex visual benchmarks. LOCI improves accuracy for both open-weight models like Qwen3-VL (+12.1 on V*, +5.8 on HR-Bench and +11.2 on VisualProbe-Hard) and proprietary models like Gemini 2.5 Pro (+8.9 on V*, +4.3 on HR-Bench, +4.8 on VisualProbe-Hard).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30959 — 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 2026-10-17T07:28:26.928Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).