{"ID":2854343,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14184","arxiv_id":"2510.14184","title":"MAFA: A Multi-Agent Framework for Enterprise-Scale Annotation with Configurable Task Adaptation","abstract":"We present MAFA (Multi-Agent Framework for Annotation), a production-deployed system that transforms enterprise-scale annotation workflows through configurable multi-agent collaboration. Addressing the critical challenge of annotation backlogs in financial services, where millions of customer utterances require accurate categorization, MAFA combines specialized agents with structured reasoning and a judge-based consensus mechanism. Our framework uniquely supports dynamic task adaptation, allowing organizations to define custom annotation types (FAQs, intents, entities, or domain-specific categories) through configuration rather than code changes. Deployed at JP Morgan Chase, MAFA has eliminated a 1 million utterance backlog while achieving, on average, 86% agreement with human annotators, annually saving over 5,000 hours of manual annotation work. The system processes utterances with annotation confidence classifications, which are typically 85% high, 10% medium, and 5% low across all datasets we tested. This enables human annotators to focus exclusively on ambiguous and low-coverage cases. We demonstrate MAFA's effectiveness across multiple datasets and languages, showing consistent improvements over traditional and single-agent annotation baselines: 13.8% higher Top-1 accuracy, 15.1% improvement in Top-5 accuracy, and 16.9% better F1 in our internal intent classification dataset and similar gains on public benchmarks. This work bridges the gap between theoretical multi-agent systems and practical enterprise deployment, providing a blueprint for organizations facing similar annotation challenges.","short_abstract":"We present MAFA (Multi-Agent Framework for Annotation), a production-deployed system that transforms enterprise-scale annotation workflows through configurable multi-agent collaboration. Addressing the critical challenge of annotation backlogs in financial services, where millions of customer utterances require accurat...","url_abs":"https://arxiv.org/abs/2510.14184","url_pdf":"https://arxiv.org/pdf/2510.14184v1","authors":"[\"Mahmood Hegazy\",\"Aaron Rodrigues\",\"Azzam Naeem\"]","published":"2025-10-16T00:30:08Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.CL\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}