[2601.04497] Vision-Language Agents for Interactive Forest Change Analysis

Computer Science > Computer Vision and Pattern Recognition arXiv:2601.04497 (cs) [Submitted on 8 Jan 2026 (v1), last revised 30 Mar 2026 (this version, v2)] Title:Vision-Language Agents for Interactive Forest Change Analysis Authors:James Brock, Ce Zhang, Nantheera Anantrasirichai View a PDF of the paper titled Vision-Language Agents for Interactive Forest Change Analysis, by James Brock and 2 other authors View PDF HTML (experimental) Abstract:Modern forest monitoring workflows increasingly benefit from the growing availability of high-resolution satellite imagery and advances in deep learning. Two persistent challenges in this context are accurate pixel-level change detection and meaningful semantic change captioning for complex forest dynamics. While large language models (LLMs) are being adapted for interactive data exploration, their integration with vision-language models (VLMs) for remote sensing image change interpretation (RSICI) remains underexplored. To address this gap, we introduce an LLM-driven agent for integrated forest change analysis that supports natural language querying across multiple RSICI tasks. The proposed system builds upon a multi-level change interpretation (MCI) vision-language backbone with LLM-based orchestration. To facilitate adaptation and evaluation in forest environments, we further introduce the Forest-Change dataset, which comprises bi-temporal satellite imagery, pixel-level change masks, and multi-granularity semantic change captions...