# Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents

arXiv: https://arxiv.org/abs/2609.12533 · HTML: https://mlsanity.com/paper/2609.12533/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 70 of its 86 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 70)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [SpectralGPT: Spectral Remote Sensing Foundation Model](https://mlsanity.com/paper/2311.07113/) (2023)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [RSVQA: Visual Question Answering for Remote Sensing Data](https://mlsanity.com/paper/2003.07333/) (2020)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model](https://mlsanity.com/paper/2402.02544/) (2024)
- [AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data](https://mlsanity.com/paper/2507.22291/) (2025)
- [VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2406.12384/) (2024)
- [SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model](https://mlsanity.com/paper/2401.09712/) (2024)
- [SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding](https://mlsanity.com/paper/2406.10100/) (2024)
- [VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis](https://mlsanity.com/paper/2403.20213/) (2024)
- [EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues](https://mlsanity.com/paper/2412.15190/) (2024)
- [HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model](https://mlsanity.com/paper/2406.11519/) (2024)
- [TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data](https://mlsanity.com/paper/2410.06234/) (2024)
- [Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis](https://mlsanity.com/paper/2403.19646/) (2024)
- [GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing](https://mlsanity.com/paper/2501.13925/) (2025)
- [GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks](https://mlsanity.com/paper/2411.19325/) (2024)
- [XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?](https://mlsanity.com/paper/2503.23771/) (2025)
- [RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent](https://mlsanity.com/paper/2406.07089/) (2024)
- [ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks](https://mlsanity.com/paper/2505.23752/) (2025)
- [Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents](https://mlsanity.com/paper/2509.23141/) (2025)
- [Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network](https://mlsanity.com/paper/2408.05475/) (2024)
- [Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data](https://mlsanity.com/paper/2401.17600/) (2024)

## Abstract (arXiv)

Real-world Earth observation (EO) agents must translate high-level scientific questions into executable workflows to acquire observations, prepare data, perform domain computations, and derive conclusions from runtime evidence. Existing EO agents typically start from supplied observations, while benchmarks typically provide prepared inputs or candidate answers, leaving full-chain open-world EO execution largely untested. We present Earth-Agent-Pro, an execution-adaptive Plan-and-Execute framework using expert-authored skills to constrain planning and runtime tool use. Workflow-centered structured memory records planned steps, accepted evidence, and their dependencies, enabling repair of only the affected workflow suffix when runtime evidence invalidates a step. Separate large language model adapters use sequence-level supervised fine-tuning for planner workflow composition and node-level group relative policy optimization with locally verifiable rewards for executor tool-argument grounding. Earth-Bench-Pro instantiates 248 expert-curated task cores as 744 questions under three matched regimes. Its 248 Open-World Execution questions span RGB imagery, spectral observations, and remote sensing products, pairing high-level requests with runtime data requirements, executable trajectories, and open-ended answers grounded in execution evidence. With a shared GPT-5 backbone, Earth-Agent-Pro achieves 66.13% LLM-as-Judge accuracy, exceeding ReAct by 20.95 points in this metric and 24.44 points in Tools-In-Order. Joint adapter tuning raises Qwen3.5-9B LLM-as-Judge accuracy from 38.31% to 50.00%, an 11.69-point gain over the untuned configuration. Planning-only evaluation and execution with the reference workflow show that the adapters improve workflow composition and argument grounding, respectively. Code and datasets will be released soon.