FinVerse: An Autonomous Agent System for Versatile Financial Analysis

TL;DR

FinVerse is an autonomous agent system for financial analysis that integrates extensive APIs, an embedded code interpreter, and optimized LLMs, demonstrating improved performance and providing open-source datasets for future research.

Contribution

The paper introduces FinVerse, a versatile financial agent system with integrated APIs, a code interpreter, and a novel LLM training scheme, addressing practical challenges in financial AI applications.

Findings

FinVerse outperforms existing systems in financial data processing.

The embedded code interpreter enhances complex data analysis capabilities.

Open-source dataset supports further development of financial AI agents.

Abstract

With the significant advancements in cognitive intelligence driven by LLMs, autonomous agent systems have attracted extensive attention. Despite this growing interest, the development of stable and efficient agent systems poses substantial practical challenges. In this paper, we introduce FinVerse, a meticulously crafted agent system designed for a broad range of financial topics. FinVerse integrates over 600 financial APIs, enabling access to more accurate and extensive financial information compared to generalist agents. To enhance financial information processing capabilities, FinVerse is equipped with an embedded code interpreter, enabling the execution of complex data analysis tasks with precision and efficiency. Our work includes an empirical comparison of several LLMs in driving FinVerse. Specifically, we propose our own scheme for training LLMs using SFT to optimize LLM performance within FinVerse. Recognizing the scarcity of specialized datasets to build LLMs for agents, we have constructed a dataset and plan to make it open-source, providing a valuable resource for peer application developers. The demo video has been released on YouTube at https://www.youtube.com/watch?v=sk8L9_Wv7J4