← Back to all news
arXiv Computer Vision By Jiachen Guo, Xinshan Zhu, Boyun Wang, Yanyan Liang, Jun Wan, Feng Lin, Ajian Liu

LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency

Read the original on arXiv Computer Vision →

LocalAgent is a collaborative framework that combines a general multimodal large language model (MLLM) with lightweight specialist verifiers to verify fine‑grained instance‑level consistency between images. The MLLM first identifies suspicious local regions, which are then examined by the Local Evidence Verifier (LEV) toolkit—comprising Local Appearance Consistency (LAC) and Local Geometric Correspondence (LGC)—to provide structured scalar evidence for the final decision. Experiments demonstrate a 4.9% accuracy gain over the strongest baseline while invoking the verifier on only 12.13% of samples, preserving the MLLM’s general multimodal capabilities.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jul 21

Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs

arXiv:2607. 16311v1 Announce Type: cross Abstract: Vision-language models (VLMs) often answer visual questions using learned language and category priors rather than grounding their predictions in the image itself.

By Jingyu Sun, Jiachen Tu, Yuyang Xue, Yaoxin Jiang, Guoyi Xu, Zhengtao Yao, Rui Qian, Yizheng Sun, Hongpeng Zhou, Jingyuan Sun, Yan Lin
llmsagentsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Oct 7

FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs

The paper introduces FindIt, the first comprehensive benchmark for evaluating the promptable localization abilities of generalist multimodal large language models (MLLMs). It covers four core task categories—object detection, referring expression detection, instance-level detection, and video-based detection—and provides a unified framework that standardizes inputs, enforces parsable bounding box outputs, and defines transparent evaluation protocols. Using this benchmark, the authors assess a range of open-source and proprietary MLLMs, revealing both their strengths and limitations, particularly their sensitivity to formatting constraints and difficulty generalizing to minor variations.

By Eshika Khandelwal, Jingjing Pan, Mingfang Zhang, Quan Kong, Lorenzo Garattoni, Hilde Kuehne
llmsagentscomputer-visionnlpmultimodalbenchmarks
More like this →
arXiv Computer Vision
Oct 12

TerraAgent: Demonstration-Grounded Multi-Agent Reasoning for Long-Context Remote Sensing Visual Question Answering

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
llmsagentsnlpfine-tuningmultimodalbenchmarkssafety
More like this →