While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory. In this paper, we formulate the Equity Research Report (ERR) Generation task for the first time. To address the data scarcity and the evaluation metrics absence, we present an open-source evaluation benchmark for ERR generation - FinRpt. We frame a Dataset Construction Pipeline that integrates 7 financial data types and produces a high-quality ERR dataset automatically, which could be used for model training and evaluation. We also introduce a comprehensive evaluation system including 11 metrics to assess the generated ERRs. Moreover, we propose a multi-agent framework specifically tailored to address this task, named FinRpt-Gen, and train several LLM-based agents on the proposed datasets using Supervised Fine-Tuning and Reinforcement Learning. Experimental results indicate the data quality and metrics effectiveness of the benchmark FinRpt and the strong performance of FinRpt-Gen, showcasing their potential to drive innovation in the ERR generation field. All code and datasets are publicly available.

翻译：尽管大语言模型在股票预测、问答等金融任务中取得了显著成功，但将其应用于完全自动化生成权益研究报告仍属未充分探索的领域。本文首次系统性地提出了权益研究报告生成任务。针对数据稀缺与评估标准缺失的问题，我们推出了一个开源的权益研究报告生成评估基准——FinRpt。我们构建了一个数据集构建流程，该流程整合了7类金融数据源，并自动生成高质量的权益研究报告数据集，可用于模型训练与评估。同时，我们引入了一套包含11项指标的综合评估体系，用以量化生成报告的质量。此外，我们提出了一个专门针对此任务设计的、名为FinRpt-Gen的多智能体框架，并利用监督微调与强化学习在构建的数据集上训练了多个基于大语言模型的智能体。实验结果表明，基准数据集FinRpt具备高质量的数据与有效的评估指标，且FinRpt-Gen框架展现出强劲的性能，彰显了二者在推动权益研究报告生成领域创新方面的潜力。所有代码与数据集均已公开。