# DisasterAgent: An Evidence-Driven Agent for Verifiable Disaster Report Generation From Remote Sensing Imagery

**Authors:** Zhijian Li, Jiawei Song, Chao Ren, Yidan Zhang, Peijin Wang, Xian Sun, Kun Fu  
**Published:** 10 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.13776) · [PDF](https://arxiv.org/pdf/2611.13776) · [Code](https://github.com/ZhijianLi2003/DisasterAgent) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.13776.html)

## Abstract

Remote sensing disaster assessment is moving from simple damage classification toward comprehensive report-level analysis. In this setting, responders need not only damage descriptions but also verifiable evidence to guide response and recovery. Recent vision-language models (VLMs) and tool-augmented agents offer strong multimodal reasoning and perception, but they struggle to provide the evidence required for high-stakes verification. To address these limitations, we propose DisasterAgent, an evidence-driven agent that uses a Perception-Augmentation-Generation workflow to generate verifiable disaster reports from bitemporal optical imagery. DisasterAgent first invokes a specialized vision expert toolkit in the perception phase to build a Spatiotemporal Perception Graph (STPG), serving as a structured memory to store and organize disaster-induced changes across space and time. Evidence-based Augmentation (EA) then extracts evidence from the STPG, attaching inline citations that form a closed evidence loop from each statement to the supporting visual evidence. Extensive experiments on the DisasterM3 and RSCC benchmarks demonstrate that DisasterAgent consistently outperforms general-domain VLMs, remote sensing-specialized models, and existing remote sensing agents. Notably, compared with the original model, it improves the average score for disaster report generation on DisasterM3 by 13.5\% and ST5-SCS on RSCC by 15.34\%, providing a more accurate and verifiable solution for disaster emergency response. The code will be available at https://github.com/ZhijianLi2003/DisasterAgent.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.