Our Research
Explore our suite of open-source tools designed to democratize AI in finance. From trading agents to LLMs.
Our Papers
Research publications and contributions
Hongyang Yang, X. Liu, and C.D. Wang. FinGPT: Open-Source Financial Large Language Models. arXiv preprint arXiv:2306.06031, 2023.
FinGPT is an open-source financial large language model ecosystem initiated, formally defined, and continuously stewarded by the AI4Finance Foundation.
This paper constitutes the first official and canonical academic definition of the FinGPT framework. It was accepted and presented at the FinLLM Workshop @ IJCAI 2023 (August 2023).
FinGPT is the first open-source LLM framework for the financial domain, providing an end-to-end, deployment-oriented pipeline for financial model construction—from data curation and efficient adaptation to real-world applications such as trading, analysis, and decision support—within a transparent and reproducible open-source ecosystem.
First official FinGPT paper, presented at the FinLLM Workshop @ IJCAI 2023 (August 2023).
Hongyang Yang, B. Zhang, Y. She, X. Liao, X. Zhang. FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading. arXiv preprint arXiv:2603.21330, 2025.
FinRL-X is a modular, deployment-consistent trading architecture that unifies data processing, strategy construction, backtesting, and broker execution under a weight-centric interface.
It provides a composable strategy pipeline integrating stock selection, portfolio allocation, timing, and risk overlays, with support for both rule-based and AI-driven components—including reinforcement learning allocators and LLM-based sentiment signals.
The framework bridges the gap between research and production by ensuring system-level consistency between backtesting evaluation and live deployment, enabling reproducible, end-to-end quantitative trading research.
Latest FinRL paper, FinRL-X, introducing the next-generation AI-native infrastructure for quantitative trading, presented at the DMO-FinTech Workshop @ PAKDD 2026.
Hongyang Yang, B. Zhang, N. Wang, C. Guo, X. Zhang, L. Lin, J. Wang, T. Zhou, M. Guan, R. Zhang, and C.D. Wang. FinRobot: An Open-Source AI Agent Platform for Financial Applications using Large Language Models. arXiv preprint arXiv:2405.14767, 2024.
FinRobot is an open-source AI agent platform for financial applications, bridging the gap between finance and AI communities using large language models.
The platform comprises four layers: financial AI agents leveraging Chain-of-Thought reasoning, LLM algorithms for task-specific strategies, operations infrastructure for model training, and foundation models.
FinRobot democratizes sophisticated financial analysis tools for both professional analysts and general users, enabling AI-powered financial decision-making at scale.
First official FinRobot paper, introducing an open-source AI agent platform for financial applications using LLMs.
Core Projects
The pillars of our ecosystem
Mature Projects
Production-ready libraries
Incubating Projects
Experimental & Research