Regulatory compliance is a complex and resource-intensive framework in the banking and financial sector, comprising multiple use cases. This research focuses on one of its most foundational and labour-intensive components: information extraction from annual reports. In collaboration with an international bank, the study investigates the automation of this process using advanced Retrieval-Augmented Generation (RAG) techniques. Specifically, it evaluates the emerging paradigm of Agentic RAG in comparison to traditional RAG workflows. The research further benchmarks the performance of leading foundation models; Mistral, OpenAI, and LLaMA within the RAG pipeline to assess their suitability for compliance-related document understanding. The primary objective is to determine the effectiveness of autonomous retrieval strategies in enhancing the accuracy and efficiency of ESG data extraction. By aligning cutting-edge developments in agentic AI with real-world industry needs, this study contributes to academic research on intelligent document processing while delivering a practical proof of concept for large-scale regulatory automation.