Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.16343 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914493880074240 |
|---|---|
| author | Yu, Chung-En Johnny Jalaian, Brian Bastian, Nathaniel D. |
| author_facet | Yu, Chung-En Johnny Jalaian, Brian Bastian, Nathaniel D. |
| contents | Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inference typically provides; yet, retraining large models is often computationally expensive and data intensive. We present Visual Reasoning Agent (VRA), a training-free agentic visual reasoning framework that orchestrates off-the-shelf large vision-language models (LVLMs) with a large reasoning model (LRM) through an iterative Think-Critique-Act loop for cross-model verification, self-critique, and recursive refinement. On the remote sensing benchmark VRSBench VQA dataset, VRA consistently outperforms multiple standalone LVLM baselines and achieves up to 40.67\% improvement on challenging question types spanning both perception and reasoning tasks. In addition, integrating three LVLMs with VRA improves the overall accuracy of the standalone LVLMs from 52.8% to 78.8%, demonstrating the effectiveness of agentic reasoning with increased inference-time compute. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16343 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Visual Reasoning Agent: Robust Vision Systems in Remote Sensing via Inference-Time Scaling Yu, Chung-En Johnny Jalaian, Brian Bastian, Nathaniel D. Computer Vision and Pattern Recognition Artificial Intelligence Multiagent Systems Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inference typically provides; yet, retraining large models is often computationally expensive and data intensive. We present Visual Reasoning Agent (VRA), a training-free agentic visual reasoning framework that orchestrates off-the-shelf large vision-language models (LVLMs) with a large reasoning model (LRM) through an iterative Think-Critique-Act loop for cross-model verification, self-critique, and recursive refinement. On the remote sensing benchmark VRSBench VQA dataset, VRA consistently outperforms multiple standalone LVLM baselines and achieves up to 40.67\% improvement on challenging question types spanning both perception and reasoning tasks. In addition, integrating three LVLMs with VRA improves the overall accuracy of the standalone LVLMs from 52.8% to 78.8%, demonstrating the effectiveness of agentic reasoning with increased inference-time compute. |
| title | Visual Reasoning Agent: Robust Vision Systems in Remote Sensing via Inference-Time Scaling |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2509.16343 |