aiqbench analysis
This research introduces IRSTD-Agent, an agentic framework that leverages multimodal large language models (MLLMs) to dynamically control visual search tools for precise infrared small-target detection. By employing Zoom-guided Interaction Learning, the system adaptively inspects images at varying scales to gather fine-grained evidence, significantly outperforming existing vision-language models in maritime and aerial surveillance tasks. The work represents a notable advancement in applying autonomous agent architectures to specialized computer vision problems where traditional MLLM approaches previously struggled with localization accuracy.
IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning
arXiv:2610.05342v1 Announce Type: cross Abstract: Infrared small-target detection plays an important role in maritime monitoring and aerial surveillance. Although multimodal large language models (MLLMs) offer promising capabilities for visual understanding, existing MLLM-based approaches struggle to precisely localize infrared small targets. In this paper, we propose IRSTD-Agent, an agentic framework for infrared small target detection through dynamic visual search. The framework enables an MLLM to adaptively determine where and at what scale to inspect an image and progressively gather fine-grained visual evidence for precise target localization. Five complementary visual tools (PROPOSAL, ZOOM, DETECT, DROP and REFINE) support object candidate discovery, adaptive observation, target localization, hypothesis rejection, and target extent refinement, together enabling a coordinated search process over original-resolution images. To teach the MLLMs to conduct this search, we introduce Zoom-guided Interaction Learning, which uses annotation-derived interaction trajectories to supervise tool selection and the corresponding arguments. Through extensive experiments on WideIRSTD-Full and IRSTD-1k datasets, we demonstrate that IRSTD-Agent outperforms the evaluated vision-language models and enhances the precise localization capabilities of MLLMs in IRSTD tasks.
Abstract:Infrared small-target detection plays an important role in maritime monitoring and aerial surveillance. Although multimodal large language models (MLLMs) offer promising capabilities for visual understanding, existing MLLM-based approaches struggle to precisely localize infrared small targets. In this paper, we propose IRSTD-Agent, an agentic framework for infrared small target detection through dynamic visual search. The framework enables an MLLM to adaptively determine where and at what scale to inspect an image and progressively gather fine-grained visual evidence for precise target localization. Five complementary visual tools (PROPOSAL, ZOOM, DETECT, DROP and REFINE) support object candidate discovery, adaptive observation, target localization, hypothesis rejection, and target extent refinement, together enabling a coordinated search process over original-resolution images. To teach the MLLMs to conduct this search, we introduce Zoom-guided Interaction Learning, which uses annotation-derived interaction trajectories to supervise tool selection and the corresponding arguments. Through extensive experiments on WideIRSTD-Full and IRSTD-1k datasets, we demonstrate that IRSTD-Agent outperforms the evaluated vision-language models and enhances the precise localization capabilities of MLLMs in IRSTD tasks.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.05342 [cs.CV]
(or arXiv:2610.05342v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.05342 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 267 words
Related coverage
2026.10: You are here 📍
Home Assistant · Oct 7, 2026
LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection
arXiv · Aug 5, 2026
Breaking Self-Attention Failure: Rethinking Query Initialization for Infrared Small Target Detection
arXiv · Aug 5, 2026
ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection
arXiv · Sep 2, 2026