Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response

• URL: http://arxiv.org/abs/2510.12061v1
• Date: Tue, 14 Oct 2025 01:59:02 GMT
• Title: Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response
• Authors: Yiheng Chen, Lingyao Li, Zihui Ma, Qikai Hu, Yilun Zhu, Min Deng, Runlong Yu,
• Abstract summary: Existing statistical approaches often lack semantic context, generalize poorly across events, and offer limited interpretability.<n>We introduce a Geospatial Awareness Layer (GAL) that grounds LLM agents in structured earth data.<n>GAL automatically retrieves and integrates infrastructure, demographic, terrain, and weather information from external geo databases.<n>This enriched context enables agents to produce evidence-based resource-allocation recommendations.
• Score: 9.801192259936888
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective disaster response is essential for safeguarding lives and property. Existing statistical approaches often lack semantic context, generalize poorly across events, and offer limited interpretability. While Large language models (LLMs) provide few-shot generalization, they remain text-bound and blind to geography. To bridge this gap, we introduce a Geospatial Awareness Layer (GAL) that grounds LLM agents in structured earth data. Starting from raw wildfire detections, GAL automatically retrieves and integrates infrastructure, demographic, terrain, and weather information from external geodatabases, assembling them into a concise, unit-annotated perception script. This enriched context enables agents to produce evidence-based resource-allocation recommendations (e.g., personnel assignments, budget allocations), further reinforced by historical analogs and daily change signals for incremental updates. We evaluate the framework in real wildfire scenarios across multiple LLM models, showing that geospatially grounded agents can outperform baselines. The proposed framework can generalize to other hazards such as floods and hurricanes.

Related papers

• OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents [68.85365034738534]
  We introduce a unified framework for developing tool-augmented geospatial agents trained on satellite imagery, natural-language queries, and detailed reasoning traces.<n>The training pipeline relies on supervised fine-tuning over structured reasoning trajectories, aligning the model with verified multistep tool interactions.<n>The accompanying corpus comprises 14,538 training and 1,169 evaluation instances, with more than 100K reasoning steps in the training split and over 7K reasoning steps in the evaluation split.
  arXiv  Detail & Related papers  (2026-02-19T18:59:54Z)
• Agentic Spatio-Temporal Grounding via Collaborative Reasoning [80.83158605034465]
  Temporal Video Grounding aims to retrieve thetemporal tube of a target object or person in a video given a text query.<n>We propose the Agentic Spatio-Temporal Grounder (ASTG) framework for the task of STVG towards an open-world and training-free scenario.<n>Specifically, two specialized agents SRA (Spatial Reasoning Agent) and TRA (Temporal Reasoning Agent) constructed leveraging on modern Multimoal Large Language Models (MLLMs)<n>Experiments on popular benchmarks demonstrate the superiority of the proposed approach where it outperforms existing weakly-supervised and zero-shot approaches by a margin
  arXiv  Detail & Related papers  (2026-02-10T10:16:27Z)
• Large Language Models for Geolocation Extraction in Humanitarian Crisis Response [0.0]
  This paper investigates whether Large Language Models can address geographic disparities in extracting location information from humanitarian documents.<n>We introduce a two-step framework that combines few-shot LLM-based named entity recognition with an agent-based geocoding module.<n>Results show that LLM-based methods substantially improve both the precision and fairness of geolocation extraction from humanitarian texts.
  arXiv  Detail & Related papers  (2026-02-09T16:34:25Z)
• Event Extraction in Large Language Model [99.94321497574805]
  We argue that EE should be viewed as a system component that provides a cognitive scaffold for LLM centered solutions.<n>This survey covers EE in text and multimodal settings, organizing tasks and taxonomy, tracing method evolution from rule based and neural models to instruction driven and generative frameworks.
  arXiv  Detail & Related papers  (2025-12-22T16:22:14Z)
• Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning [63.109585527799005]
  GroundingAgent is a visual grounding framework that operates without task-specific fine-tuning.<n>It achieves an average zero-shot grounding accuracy of 65.1 % on widely-used benchmarks.<n>It also offers strong interpretability, transparently illustrating each reasoning step.
  arXiv  Detail & Related papers  (2025-11-24T03:11:08Z)
• FireScope: Wildfire Risk Prediction with a Chain-of-Thought Oracle [69.84129020970477]
  Existing methods lack the causal reasoning and understanding required for reliable generalization.<n>We introduce $textbfFireScope-Bench, a dataset and benchmark that couples Sentinel-2 imagery and climate data with expert-defined risks.<n>When trained in the USA and tested in Europe, $textbfFireScope$ achieves substantial performance gains.<n>Our findings demonstrate that reasoning can ground prediction models, improving both generalization and interpretability.
  arXiv  Detail & Related papers  (2025-11-21T11:45:22Z)
• Subnational Geocoding of Global Disasters Using Large Language Models [0.04374837991804084]
  Subnational location data of disaster events are critical for risk assessment and disaster risk reduction.<n>Disaster databases report locations in unstructured textual form, with inconsistent granularity or spelling, that make it difficult to integrate with spatial datasets.<n>We present a fully automated LLM-assisted workflow that processes and cleans textual location information using GPT-4o.
  arXiv  Detail & Related papers  (2025-11-13T17:04:18Z)
• ALIGN: A Vision-Language Framework for High-Accuracy Accident Location Inference through Geo-Spatial Neural Reasoning [0.0]
  Most low- and middle-income countries face a critical shortage of accurate, location-specific crash data.<n>Existing text-based geocoding tools perform poorly in multilingual and unstructured news environments.<n>This study introduces ALIGN, a vision-language framework that emulates human spatial reasoning to infer accident coordinates.
  arXiv  Detail & Related papers  (2025-11-09T10:44:26Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains [21.472335458132477]
  Geo Reason Enhancement (GRE) Suite is a novel framework that augments Visual Language Models with structured reasoning chains for interpretable location inference.<n>First, we introduce GRE30K, a high-quality geo-localization reasoning dataset designed to facilitate fine-grained visual and contextual analysis.<n>Next, we present the GRE model, which employs a multi-stage reasoning strategy to progressively infer scene attributes, local details, and semantic features, thereby narrowing down potential geographic regions with enhanced precision.
  arXiv  Detail & Related papers  (2025-05-24T13:48:57Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework [51.26566634946208]
  We introduce smileGeo, a novel visual geo-localization framework. By inter-agent communication, smileGeo integrates the inherent knowledge of these agents with additional retrieved information. Results show that our approach significantly outperforms current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-21T03:31:30Z)
• Into the Unknown: Generating Geospatial Descriptions for New Environments [18.736071151303726]
  Rendezvous task requires reasoning over allocentric spatial relationships. Using opensource descriptions paired with coordinates (e.g., Wikipedia) provides training data but suffers from limited spatially-oriented text. We propose a large-scale augmentation method for generating high-quality synthetic data for new environments.
  arXiv  Detail & Related papers  (2024-06-28T14:56:21Z)
• GOMAA-Geo: GOal Modality Agnostic Active Geo-localization [49.599465495973654]
  We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. GOMAA-Geo is a goal modality active geo-localization agent for zero-shot generalization between different goal modalities.
  arXiv  Detail & Related papers  (2024-06-04T02:59:36Z)
• Toward Foundation Models for Earth Monitoring: Generalizable Deep Learning Models for Natural Hazard Segmentation [0.47725505365135473]
  Near real-time mapping of natural hazards is an emerging priority for disaster relief, risk management, and informing governmental policy decisions. Recent methods to achieve near real-time mapping increasingly leverage deep learning (DL) We propose a methodology to significantly improve the generalizability of DL natural hazards mappers based on pre-training on a suitable pre-task.
  arXiv  Detail & Related papers  (2023-01-23T08:35:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.