mlsanityData to 14 Oct 2026

MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems

arXiv 2604.07956 ↗First posted 9 Apr 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Industry classification schemes are integral parts of public and corporate databases as they classify businesses based on economic activity. Due to the size of the company registers, manual annotation is costly, and fine-tuning models with every update in industry classification schemes requires significant data collection. We replicate the manual expert verification by using existing or easily retrievable multimodal resources for industry classification. We present MONETA, the first multimodal industry classification benchmark with text (Website, Wikipedia, Wikidata) and geospatial sources (OpenStreetMap and satellite imagery). Our dataset enlists 1,000 businesses in Europe with 20 economic activity labels according to EU guidelines (NACE). Our training-free baseline reaches 62.10% and 74.10% with open and closed-source Multimodal Large Language Models (MLLM). We observe an increase of up to 22.80% with the combination of multi-turn design, context enrichment, and classification explanations. We will release our dataset and the enhanced guidelines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 48 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

13 of 48 references.

References · 13

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  3. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  4. 2023Large Language Modelscited by 780
  5. 2016AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classificationcited by 347
  6. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimizationcited by 239
  7. 2024RS-Agent: Automating Remote Sensing Tasks through Intelligent Agentcited by 49
  8. 2025Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Frameworkcited by 24
  9. 2024FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understandingcited by 11
  10. 2018AID++: An Updated Version of AID on Scene Classificationcited by 3
  11. 2023Company classification using zero-shot learningcited by 2
  12. 2024Identifying Spatio-Temporal Drivers of Extreme Eventscited by 1
1 more
  1. 2025Measuring and Mitigating Hallucinations in Vision-Language Dataset Generation for Remote Sensingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Automated Analysis of Sustainability Reports: Using Large Language Models for the Extraction and Prediction of EU Taxonomy-Compliant KPIs
  2. 2024Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
  3. 2024MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning
  4. 2026When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents
  5. 2025FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information
  6. 2023FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis
  7. 2026CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition
  8. 2025CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model