FinSight: Towards Real-World Financial Deep Research
This addresses the labor-intensive process of financial report generation for professionals, though it appears incremental as it builds on existing multi-agent and visualization methods.
The paper tackled the problem of automating professional financial report generation by introducing FinSight, a multi-agent framework that significantly outperformed baselines in factual accuracy, analytical depth, and presentation quality, demonstrating a clear path toward human-expert quality reports.
Generating professional financial reports is a labor-intensive and intellectually demanding process that current AI systems struggle to fully automate. To address this challenge, we introduce FinSight (Financial InSight), a novel multi agent framework for producing high-quality, multimodal financial reports. The foundation of FinSight is the Code Agent with Variable Memory (CAVM) architecture, which unifies external data, designed tools, and agents into a programmable variable space, enabling flexible data collection, analysis and report generation through executable code. To ensure professional-grade visualization, we propose an Iterative Vision-Enhanced Mechanism that progressively refines raw visual outputs into polished financial charts. Furthermore, a two stage Writing Framework expands concise Chain-of-Analysis segments into coherent, citation-aware, and multimodal reports, ensuring both analytical depth and structural consistency. Experiments on various company and industry-level tasks demonstrate that FinSight significantly outperforms all baselines, including leading deep research systems in terms of factual accuracy, analytical depth, and presentation quality, demonstrating a clear path toward generating reports that approach human-expert quality.