Metraipolis › archive › dc_5939a4e90ad3

Agentic Large Language Model Workflows for Earth Observation: Tool Orchestration, Foundation-Model Adaptation, and the Evaluation Gap (2026) · DOI 10.31223/x5tn59

Source
Metraipolis archive
Original
https://doi.org/10.31223/x5tn59
License (as archived)
CC-BY-4.0
Archived
2026-10-07T10:34:05.324Z
SHA-256 of the archived text
3df627939510a7d8415dc3bb370145930c0d21a65b6eda2fc67af5a768a76593
Stable URL of this page
https://metraipolis.com/documento/dc_5939a4e90ad3

How to cite

Agentic Large Language Model Workflows for Earth Observation: Tool Orchestration, Foundation-Model Adaptation, and the Evaluation Gap (2026) · DOI 10.31223/x5tn59 — Metraipolis archive, https://doi.org/10.31223/x5tn59 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_5939a4e90ad3 (Metraipolis archive dc_5939a4e90ad3, sha256 3df627939510a7d8415dc3bb370145930c0d21a65b6eda2fc67af5a768a76593)
BibTeX
@misc{dc5939a4e90ad3,
  title = {Agentic Large Language Model Workflows for Earth Observation: Tool Orchestration, Foundation-Model Adaptation, and the Evaluation Gap (2026) · DOI 10.31223/x5tn59},
  howpublished = {Metraipolis archive},
  url = {https://doi.org/10.31223/x5tn59},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_5939a4e90ad3; sha256 3df627939510a7d8415dc3bb370145930c0d21a65b6eda2fc67af5a768a76593},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.31223/x5tn59. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Articolo recente con licenza aperta: scheda dai metadati Crossref (posted-content).
Titolo: Agentic Large Language Model Workflows for Earth Observation: Tool Orchestration, Foundation-Model Adaptation, and the Evaluation Gap
Autori: salah alheejawi, Valentas Gruzauskas
Pubblicato: 2026-09-05 · editore: California Digital Library (CDL)
DOI: https://doi.org/10.31223/x5tn59
Licenza dell'articolo: CC-BY-4.0

Abstract (testo degli autori, CC-BY-4.0):
Large language model (LLM) agents have moved rapidly from general-purpose assistants to domain systems that orchestrate specialised remote-sensing models. Within roughly two years, geospatial agents have demonstrated reliable task planning across dozens of Earth Observation (EO) tasks, benchmark environments containing hundreds of tools, and fine-tuned open-weight controllers that outperform far larger proprietary models at generating geospatial tool-use chains. This review synthesises that literature and argues that it has converged on a common architecture with a common limit. Every system surveyed orchestrates models that human researchers built, over data that human analysts prepared; none designs a model, and none constructs its own analysis-ready data. We identify three gaps that follow from this. First, a reliability wall: reported agent success falls from above 95% on single-tool tasks to below 70% beyond eight tool calls, and scaling benchmark volume tenfold does not expose or improve this, so the binding variable is composition depth rather than data quantity. Second, a preprocessing gap: benchmark datasets arrive co-registered, temporally aligned and quality-flagged, so agents are never evaluated on the multi-source data-cube construction that dominates real EO practice. Third, an evaluation gap: automated LLM-as-judge scoring is widely reported as ground truth without calibration against human experts. We survey the open geospatial foundation models that now form the practical substrate for EO modelling, argue that adaptation strategy rather than architecture is the under-searched design variable, and set out a research agenda in which domain constraint — verified templates, physically grounded data contracts, explicit compute budgets and the capacity to refuse — is treated as the mechanism by which agentic autonomy becomes verifiable rather than merely fluent.

Fonte: https://api.crossref.org/works/10.31223%2Fx5tn59 — metadati Crossref, consultati il 2026-10-06. Interrogazione: «large language model agents tool use».