Metraipolis › archive › dc_649c98ff08de

Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs — arXiv:2608.29374

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29374
License (as archived)
CC0-1.0
Archived
2026-10-17T09:58:58.135Z
SHA-256 of the archived text
96c4e384a485f9a78bb9af894b1f222411f5df4a0d0ff75e99c09fbdba4e6f78
Stable URL of this page
https://metraipolis.com/documento/dc_649c98ff08de

How to cite

Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs — arXiv:2608.29374 — arXiv (en), https://arxiv.org/abs/2608.29374 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_649c98ff08de (Metraipolis archive dc_649c98ff08de, sha256 96c4e384a485f9a78bb9af894b1f222411f5df4a0d0ff75e99c09fbdba4e6f78)
BibTeX
@misc{dc649c98ff08de,
  title = {Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs — arXiv:2608.29374},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29374},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_649c98ff08de; sha256 96c4e384a485f9a78bb9af894b1f222411f5df4a0d0ff75e99c09fbdba4e6f78},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29374. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-augmented multimodal reasoning integrates external tools (e.g., object detection, depth estimation) into multimodal large language models (MLLMs) to address perceptual bottlenecks in complex visual tasks. However, existing approaches rarely verify tool outputs, limiting their ability to detect and recover from tool failures. We propose ReVISE, a framework that equips MLLMs with verification and dynamic error recovery for tool-augmented reasoning. ReVISE introduces (1) a curated training dataset that supervises reflective behaviors, enabling models to validate tool-derived evidence, reformulate queries when visual mismatches arise, and fall back to intrinsic grounding when external tools are unreliable; and (2) a reinforcement learning based targeted rewards that encourage internal reflection and penalize spatial misalignment. Experiments on several benchmarks demonstrate consistent improvements over existing methods, highlighting the importance of error detection and correction in tool-augmented multimodal reasoning.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.29374 — 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 2026-10-17T09:28:48.033Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).