ClueTracer is a training‑free, parameter‑free plugin that suppresses hallucinations in multimodal reasoning models by tracing how visual clues propagate from the question through the model’s reasoning pathway. It localizes task‑relevant image patches while ignoring irrelevant regions, thereby addressing the problem of reasoning drift where models over‑focus on question‑irrelevant entities. The method improves performance across various reasoning architectures by an average of 1.21× on reasoning benchmarks.
By Gongli Xi, Kun Wang, Zeming Gao, Huahui Yi, Haolang Lu, Qianshan Wei, Ye Tian, Wendong Wang
arXiv:2606. 11719v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs).
By Enhan Zhao, Wei Wu, Yuanrui Zhang, Xueliang Zhao, Di He
Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require comparing multiple instances of the same object category. We study this problem through the Closest-Instance Distance Query (CIDQ), where a model must identify the nearest visible candidate to a unique reference object and estimate their gravity-aligned floor-plane distance.
The paper introduces TerraAgent, a training‑free framework that enhances remote sensing visual question answering by integrating three modules: GDR for demonstration retrieval, MACE for evidence‑typed sub‑question decomposition, and CVA for counterfactual evidence auditing. It demonstrates significant improvements on multiple benchmarks, raising accuracy, visual‑dependency scores, and reducing prior‑only answers and hallucinations without fine‑tuning.
By Jingwen Huang, Yiming Fang, Hanxiao Wu, Boyuan He, Keyi Luo
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
By Leyuan Yu, Xiao Tang, Minghao Liu, Xinyuan Li, Xiaokai Bai, Sheng Zhou, Qunshu Lin, Weihao Xuan, Naoto Yokoya
arXiv:2606. 31745v1 Announce Type: cross Abstract: Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why.
By Ziyuan Liu, Ruifei Zhu, Ouqiao Ma, Yuantao Gu
GeoRefer-Bench is a new benchmark for verifiable geospatial referring segmentation that evaluates whether models correctly resolve spatial relations in overhead imagery. Each query is expressed as an executable logical form over a metric scene graph, and predictions are scored with Exact Query Success (EQS), requiring an exact match to the query’s referent set. The dataset contains 700 UAV scenes, 26,217 instances, 142,796 spatial relations, 20,916 executable queries across five reasoning levels, and additional paraphrases, unanswerable queries, counterfactual pairs, and leakage‑controlled splits.
By Shuaishuai Cao, Min Huang, Meng Tang, Xuan Liu, Youjin Wang, Hui Lin
PRISM-BENCH is a new benchmark comprising 1,000 expert‑curated vision‑language questions across five under‑represented reasoning categories, each paired with an idealized reasoning trace validated by a second annotator. It introduces diagnostics beyond final‑answer accuracy: a perception probe that attributes about 85% of frontier‑model failures to misperception, and trace alignment that predicts answer correctness with a macro AUROC of 0.66. The benchmark also presents CORE, an efficiency‑aware metric that reorders 24.2% of model pairs relative to accuracy while remaining uncorrelated with response length, revealing that recent gains are driven by recognition rather than spatial grounding.
By Vansh Bhatia, Mehdi Rezagholizadeh, Parsa Ashrafi Fashi, Igor Gilitschenski, Vikram Appia, Emad Barsoum
arXiv:2508. 10956v3 Announce Type: replace-cross Abstract: Inspired by human categorization, visual reasoning about object properties, such as physical attributes and functions, involves identifying and recognizing low-level details and higher-level abstractions.
By Abhishek Kolari, Mohammadhossein Khojasteh, Yifan Jiang, Floris den Hengst, Filip Ilievski
arXiv:2608. 11738v1 Announce Type: cross Abstract: Multimodal Large Language Model (MLLM)-based UAV aerial image understanding and reasoning is essential for aerial intelligence yet poses distinct challenges arising from extreme scale variation, arbitrary camera orientations, and high object density.
By Haoyu Zhang, Shuoxun Zhang, Peng Ye, Lin Zhang, Jiakang Yuan, Shenghong Yi, Yuening Wang, Tao Chen
GeoNLI introduces a unified, modular pipeline that combines advanced SAM variants with multimodal large language models to perform satellite image captioning, visual question answering (VQA), and visual grounding. The EarthMind model achieves strong results on captioning and VQA, while multiple RemoteSAM-SAM and DiffuSAM pipelines are used for grounding, ultimately employing a majority‑voting ensemble across several models. The system reports 82% captioning accuracy, 83.32% VQA accuracy, and 64.94% grounding accuracy, demonstrating improved consistency over task‑specific approaches.
By Ashutosh Gandhe, Anupam Rawat, Geet Sethi, Kabir Nasiruddin, Madhav Kotecha, Panav Shah, Rakshit Sawarn, Soumitra Nayak
arXiv:2608.22950v1 Announce Type: new
Abstract: Floating waste in inland waterways threatens aquatic ecosystems and requires timely monitoring under cluttered, multi-object conditions. Existing aquat...
By Md. Asaduzzaman Shuvo, Ahsan Farabi, Md. Abdul Ahad Minhaz, Mahedi Hasan, Israt Khandaker, Ibrahim Khalil Shanto, Muhammad Nomani Kabir