FinNextAssist：迈向专业金融深度研究助手
FinNextAssist: Towards Professional Financial Deep Research Assistant
- South China University of Technology（华南理工大学）
- National University of Singapore（新加坡国立大学）
- iFLYTEK CO., LTD（科大讯飞股份有限公司）
- Central University of Finance and Economics（中央财经大学）
- Estates（六地产）
- Hefei University of Technology（合肥工业大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出FinNextAssist，一种面向专业金融分析的四阶段深度研究框架，引入TabAgent和HeteroAgent两个轻量子智能体，在多个基准上显著超越现有DR智能体。
AI中文摘要：
深度研究（Deep Research, DR）智能体通过自主规划、迭代检索、多步推理和结构化报告，已在复杂研究型任务中展现出强大能力。然而，将DR智能体应用于金融领域带来了独特挑战：金融分析要求联合完成跨越多种数据类型、工具和分析工作流的异构子任务。我们识别出专业金融DR智能体的三个关键需求：整合权威的异构金融数据源；专门的 analytical 工具和技能；以及针对特定领域子任务的专用子智能体。基于这些原则，我们提出了FinNextAssist，一个为专业金融分析设计的端到端深度研究框架。FinNextAssist将研究过程分解为四个阶段：任务规划器（Task Planner）、证据编译器（Evidence Compiler）、推理引擎（Reasoning Engine）和报告组装器（Report Assembler），并引入了两个新颖的轻量子智能体：TabAgent，用于跨市场金融表格理解；以及HeteroAgent，用于跨模态异构金融数据解释。在FinDeepResearch、Finance Agent Benchmark和FinTMMBench-Web上的大量实验表明，FinNextAssist显著优于强大的专有和开源DR智能体，消融研究证实了各组件在不同市场和语言中的贡献。
英文摘要：
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.
