FinNextAssist improves financial research with smart data tools
FinNextAssist: Towards Professional Financial Deep Research Assistant
Multiagent Systems
Summary
Financial research needs to handle lots of different data types and complex tasks, which can be challenging for AI assistants. The authors designed FinNextAssist, a system that breaks down financial research into smaller steps and uses special sub-agents to understand tables and mixed data sources. Their tests showed that FinNextAssist performs better than existing AI agents in dealing with financial information across various markets and languages. This approach helps make financial deep research more accurate and efficient.
What this means in practice
- •For financial analysis teams: Perform comprehensive financial research workflows automatically with support for diverse data and markets.
- •For investment advisory services: Generate detailed financial reports that integrate multiple data types and analytical methods to support client advice.$Commercial implications: The framework enables producing advanced financial research reports that can be packaged as a commercial advisory tool.
Authors
Xiangyu Li, Fengbin Zhu, Xuan Yao, Siyu Liu, Xiaoluan Liu, Chao Wang, Huanbo Luan, Xiaofen Xing, Xiangmin Xu, Ke-Wei Huang, Richang Hong, Tat-Seng Chua
Abstract
Deep Research (DR) agents have demonstrated strong capabilities in complex, research-oriented tasks through autonomous planning, iterative retrieval, multi-step reasoning, and structured reporting. However, adapting DR agents to finance introduces unique challenges: financial analysis demands the joint completion of heterogeneous sub-tasks spanning diverse data types, tools, and analytical workflows. We identify three key requirements for a professional financial DR agent: integration of authoritative, heterogeneous financial data sources; specialized analytical tools and skills; and dedicated sub-agents for domain-specific sub-tasks. Building on these principles, we propose FinNextAssist, an end-to-end deep research framework designed for professional financial analysis. FinNextAssist decomposes the research process into four stages: Task Planner, Evidence Compiler, Reasoning Engine, and Report Assembler, and introduces two novel lightweight sub-agents: TabAgent, for cross-market financial table understanding, and HeteroAgent, for cross-modality heterogeneous financial data interpretation. Extensive experiments on FinDeepResearch, the Finance Agent Benchmark, and FinTMMBench-Web show that FinNextAssist substantially outperforms both strong proprietary and open-source DR agents, with ablation studies confirming the contribution of each component across diverse markets and languages.