arXiv AI By Gabriel Diaz-Ireland, Diego Prieto-Herr\'aez, Mario Garc\'ia Peces, Javier Vel\'azquez, Devika Jain

GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models

Read the original on arXiv AI →

arXiv:2606. 12821v1 Announce Type: new Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis, and AI agents that automate geospatial workflows remain unvalidated: no benchmark evaluates agents operating through structured tool calling against real APIs.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 12

TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?

arXiv:2606. 13148v1 Announce Type: new Abstract: Climate and environmental decision-making increasingly requires reasoning across heterogeneous inputs, including gridded physical data, satellite imagery, geospatial context, and simulator outputs.

By Dat Tien Nguyen, Thao Nguyen, Fadillah Adamsyah Maani, Huy M. Le, Muhammad Umer Sheikh, Numan Saeed, Muhammad Haris Khan, Salman Khan
arXiv AI
Jun 30

Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning

arXiv:2605. 24844v2 Announce Type: replace Abstract: While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evolution, current AI in Earth sciences predominantly targets surface remote sensing and GIS.

By Chenyou Guo, Zongqi Liu, Yizhou Zhang, Zhaorui Jiang, Ze Liu
arXiv AI
Jul 22

Now We Know? A Systematic Comparison of TerraMind and THOR

arXiv:2607. 18504v1 Announce Type: cross Abstract: Benchmarks for Geospatial Foundation Models (GFMs) increasingly rank models by aggregate score, but such rankings obscure why models differ: how much of the gap is architecture, how much is decoder capacity, and how much is a use-case-specific artefact?

By Frederick Schindlegger, Kenzo Bounegta, Eva Gmelich Meijling, Johannes Jakubik, Arnt-B{\o}rre Salberg, Theodor Forgaard, Nicolas Longepe, Valerio Marsocci