MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models
This work addresses a domain-specific problem for mineral exploration, but it is incremental as it builds on existing MLLM methods.
The paper tackles the challenge of using multimodal large language models for remote-sensing mineral exploration by introducing MineAgent, a modular framework that improves multi-image reasoning and spatial-spectral integration, and MineBench, a benchmark for evaluation, with experiments showing its effectiveness.
Remote-sensing mineral exploration is critical for identifying economically viable mineral deposits, yet it poses significant challenges for multimodal large language models (MLLMs). These include limitations in domain-specific geological knowledge and difficulties in reasoning across multiple remote-sensing images, further exacerbating long-context issues. To address these, we present MineAgent, a modular framework leveraging hierarchical judging and decision-making modules to improve multi-image reasoning and spatial-spectral integration. Complementing this, we propose MineBench, a benchmark specific for evaluating MLLMs in domain-specific mineral exploration tasks using geological and hyperspectral data. Extensive experiments demonstrate the effectiveness of MineAgent, highlighting its potential to advance MLLMs in remote-sensing mineral exploration.