arXiv preprint arXiv:2405.14767, 2024
DOI:
10.48550/arXiv.2405.14767
As financial institutions and professionals increasingly incorporate Large Language Models (LLMs) into their workflows, substantial barriers, including proprietary data and specialized knowledge, persist between the finance sector and the AI community. These challenges impede the AI community's ability to enhance financial tasks effectively. Acknowledging financial analysis's critical role, we aim to devise financial-specialized LLM-based toolchains and democratize access to them through open-source initiatives, promoting wider AI adoption in financial decision-making. In this paper, we introduce FinRobot, a novel open-source AI agent platform supporting multiple financially specialized AI agents, each powered by LLM. Specifically, the platform consists of four major layers: 1) the Financial AI Agents layer that formulates Financial Chain-of-Thought (CoT) by breaking sophisticated financial problems down into logical sequences; 2) the Financial LLM Algorithms layer dynamically configures appropriate model application strategies for specific tasks; 3) the LLMOps and DataOps layer produces accurate models by applying training/fine-tuning techniques and using task-relevant data; 4) the Multi-source LLM Foundation Models layer that integrates various LLMs and enables the above layers to access them directly. Finally, FinRobot provides hands-on for both professional-grade analysts and laypersons to utilize powerful AI techniques for advanced financial analysis. We open-source FinRobot at https://github.com/AI4Finance-Foundation/FinRobot.
FinRobot is an open-source financial AI agent ecosystem initiated, formally defined, and continuously stewarded by the AI4Finance Foundation.
This publication constitutes the first official and canonical academic reference for the FinRobot platform and research ecosystem. It establishes the original architecture and methodology for building financial AI agents powered by large language models.
Since its initial introduction, FinRobot has evolved into a broader open research and engineering ecosystem spanning financial research, valuation, quantitative analysis, enterprise finance, and other financial decision-making applications.
Subsequent FinRobot research explores specialized agents, agent collaboration, financial workflows, and application-specific extensions built upon the original FinRobot platform.
When referring to FinRobot as a platform, framework, ecosystem, or research line, please cite this publication as the original and canonical academic reference.
The following publications represent subsequent research and application-specific extensions of the FinRobot research ecosystem:
These publications should be treated as distinct follow-up studies within the broader FinRobot research ecosystem.
This publication, together with the official AI4Finance open-source repositories, establishes the original academic and technical foundation of the FinRobot project.
FinRobot is maintained as an open-source initiative under the AI4Finance Foundation. The official codebase, documentation, research artifacts, and ongoing development are maintained by the AI4Finance open-source community.
The FinRobot research ecosystem is supported by publicly accessible open-source software and research artifacts maintained by the AI4Finance Foundation.
@article{yang2024finrobot,
title = {FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models},
author = {Yang, Hongyang and Zhang, Boyu and Wang, Neng and Guo, Cheng and Zhang, Xiaoli and Lin, Likun and Wang, Junlin and Zhou, Tianyu and Guan, Mao and Zhang, Runjia and Wang, Christina Dan},
journal = {arXiv preprint arXiv:2405.14767},
year = {2024},
doi = {10.48550/arXiv.2405.14767},
url = {https://arxiv.org/abs/2405.14767}
}