Metraipolis › archive › dc_d166f64087e6
Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes — arXiv:2608.10954
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10954
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:09:34.195Z
- SHA-256 of the archived text
75af0c9f0d5909049af91a6856a19b17b390faf268b3d465934171495115f123- Stable URL of this page
https://metraipolis.com/documento/dc_d166f64087e6
How to cite
Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes — arXiv:2608.10954 — arXiv (en), https://arxiv.org/abs/2608.10954 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d166f64087e6 (Metraipolis archive dc_d166f64087e6, sha256 75af0c9f0d5909049af91a6856a19b17b390faf268b3d465934171495115f123)
BibTeX
@misc{dcd166f64087e6,
title = {Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes — arXiv:2608.10954},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10954},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d166f64087e6; sha256 75af0c9f0d5909049af91a6856a19b17b390faf268b3d465934171495115f123},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10954. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex scenes under adverse conditions. In these settings, models often rely on implicit inference without sufficient visual evidence, leading to a disconnect between perception and reasoning. Meanwhile, existing outcome-oriented benchmarks evaluate only final predictions and fail to diagnose failures in the underlying reasoning process. To address this gap, the authors propose AD2-Bench, which introduces a Hierarchical Visual Diagnosis framework that decomposes reasoning into a structured Chain of Evidence (CoE). This fine-grained diagnosis reveals that robust multimodal reasoning fundamentally depends on accurate evidence acquisition. Building on this perspective, the authors formulate reasoning from a probabilistic viewpoint and identify two primary causes of reasoning failure: Spatial Ambiguity, where models fail to distinguish target objects from background clutter, resulting in localization errors; and Semantic Uncertainty, where degraded visual features lead to incorrect semantic interpretation, resulting in understanding errors. To overcome these evidence deficiencies, they further propose Evidence-grounded Visual Reasoning (EGVOR), which replaces implicit reasoning with the explicit generation of Evidence Atoms - structured spatial-semantic triplets that enforce tight alignment between localization and semantic understanding. The model is trained through a hierarchical curriculum that progresses from reflective supervision construction to reinforcement learning, where reducing reasoning variance is explicitly rewarded. Extensive experiments demonstrate that EGVOR substantially improves reasoning stability under adverse conditions, providing a more robust framework for trustworthy multimodal cognition. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.10954 — 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 2026-10-19T05:57:28.417Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).