# EO-Gym: A Multimodal, Interactive Environment for Earth Observation Agents

arXiv: https://arxiv.org/abs/2605.01250 · HTML: https://mlsanity.com/paper/2605.01250/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 88 references that are in the map.
- First posted on arXiv 2 May 2026.

## Builds on (most cited first, 30 of 43)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents](https://mlsanity.com/paper/2311.05437/) (2023)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [xView: Objects in Context in Overhead Imagery](https://mlsanity.com/paper/1802.07856/) (2018)
- [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [GEO-Bench: Toward Foundation Models for Earth Monitoring](https://mlsanity.com/paper/2306.03831/) (2023)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (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)
- [EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues](https://mlsanity.com/paper/2412.15190/) (2024)
- [GTA: A Benchmark for General Tool Agents](https://mlsanity.com/paper/2407.08713/) (2024)
- [Self-attention for raw optical Satellite Time Series Classification](https://mlsanity.com/paper/1910.10536/) (2019)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)

## Built on by (most cited first, 1 of 1)

- [Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents](https://mlsanity.com/paper/2609.12533/) (2026)

## Abstract (arXiv)

Earth Observation (EO) analysis is inherently interactive: resolving uncertainty often requires expanding the region of interest, retrieving historical observations, and switching across sensors such as optical and Synthetic Aperture Radar. However, most EO benchmarks collapse this process into fixed-input, single-turn tasks. To address this gap, we present EO-Gym, a controlled executable framework for multimodal, tool-using EO agents that formulates EO analysis as a Gymnasium-style local geospatial workspace backed by more than 660k multimodal files indexed by location, time, and sensor type, with 35 EO-specialized tools spanning six task families. Built on this environment, we construct EO-Gym-Data, a benchmark of 9,078 trajectories and 34,604 reasoning steps, and grounded in eight public EO datasets together with Landsat and Sentinel-2 imagery. Evaluating 10 open and closed VLMs shows that strong general-purpose models still struggle with interactive EO reasoning, especially on temporal and cross-modal workflows. As a reference baseline, EO-Gym-4B, obtained by fine-tuning Qwen3-VL-4B-Instruct on EO-Gym-Data, improves overall Pass@3 from 0.49 to 0.74 under the main evaluation setting. O-Gym provides a reproducible environment for interactive EO agents, operationalizing EO as an evidence-gathering problem that requires planning across geospatial, temporal, and sensing modality.