# GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks

arXiv: https://arxiv.org/abs/2610.09112 · HTML: https://mlsanity.com/paper/2610.09112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 8 of 8)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models](https://mlsanity.com/paper/2412.04204/) (2024)
- [ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks](https://mlsanity.com/paper/2505.23752/) (2025)
- [GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI](https://mlsanity.com/paper/2511.15658/) (2025)
- [Towards LLM Agents for Earth Observation](https://mlsanity.com/paper/2504.12110/) (2025)
- [SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?](https://mlsanity.com/paper/2602.03916/) (2026)
- [EnviroExam: Benchmarking Environmental Science Knowledge of Large Language Models](https://mlsanity.com/paper/2405.11265/) (2024)
- [GPSBench: Do Large Language Models Understand GPS Coordinates?](https://mlsanity.com/paper/2602.16105/) (2026)

## Abstract (arXiv)

Before tool-using LLM agents are deployed in environmental and geospatial workflows, teams need evidence that an agent reliably selects the right operations against real APIs. We introduce GeoNatureAgent (GNA), a framework for pre-production evaluation of tool-using agents: a fixed sixteen-tool geospatial interface published as a Model Context Protocol (MCP) server, so the agent under test is the only variable, scored against an identical tool layer, task suite, and deterministic scorer. Its flagship instance is a 103-task benchmark (a 93-task main suite across 18 categories plus a ten-task comparison expansion) evaluated against an open, self-hostable geospatial API serving three environmental indicators across Spain and Portugal. We evaluate nine LLMs under three temperature-1.0 seeds, reporting capability and per-case cost as orthogonal axes. (1) Claude Sonnet 4 achieves the highest capability (61.7% +/- 0.7% on all 103 tasks; 60.8% on the main suite), followed closely by DeepSeek V3.2 (57.9%), while no other model exceeds 53%; (2) the cost-accuracy Pareto frontier is mostly open-weight, with DeepSeek V3.2 offering 93% of Claude's capability at 11.3x lower list-price cost; (3) under strict all-checks scoring the best model sits 24-36 points below the 85-97% reported on general-purpose GIS benchmarks, whereas per-check partial credit for the top four models (86-90%) is comparable, so much of that gap reflects scoring strictness rather than task difficulty alone. The MCP server, evaluation harness, benchmark, and API are publicly available; swapping the tool executors and task suite instantiates an equivalent benchmark for any geospatial domain.