GeoDecider uses LLMs for explainable, coarse-to-fine lithology classification

Researchers have introduced GeoDecider, a novel agentic workflow designed for explainable lithology classification. This system mimics expert geologists by employing a coarse-to-fine reasoning process that integrates a base classifier with tool-augmented analysis and geological refinement. Experiments indicate that GeoDecider surpasses existing methods in accuracy and interpretability while optimizing inference efficiency. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a new framework for applying LLMs to geological classification tasks, potentially improving subsurface analysis accuracy and interpretability.

RANK_REASON The cluster contains an academic paper detailing a new methodology for lithology classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• GeoDecider
• LLM

• paper
• other