Model Releases
MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems
arXiv:2604.07956v2 Announce Type: replace Abstract: Industry classification schemes are integral parts of public and corporate databases as they classify businesses based on economic activity. Due to
arXiv:2604.07956v2 Announce Type: replace Abstract: 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.
Related
- Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems
- When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
- STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
- From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI
- Towards Knowledgeable Deep Research: Framework and Benchmark
Source: arXiv cs.AI | 2026-04-13