Athenarabetaathenara:~$ registry cite papers/finagent-paper
A Multimodal Foundation Agent for Financial Trading (FinAgent)
Presents FinAgent, a multimodal trading agent that processes numerical, textual, and visual market data with dual-level reflection and diversified memory retrieval.
added 2026-08-15 · external
$ git clone https://github.com/DVampire/FinAgent@article{finagent-paper, title = {A Multimodal Foundation Agent for Financial Trading (FinAgent)}, author = {Wentao Zhang and Lingxuan Zhao and Haochong Xia and Shuo Sun and Jiaze Sun and Molei Qin and Xinyi Li and Yuqing Zhao and Yilei Zhao and Xinyu Cai and Longtao Zheng and Xinrun Wang and Bo An}, year = {2024}, eprint = {2402.18485}, archiveprefix = {arXiv}, note = {KDD 2024}, }
FinAgent’s market intelligence module ingests numerical series, text, and chart images, while a dual-level reflection mechanism supports both rapid adaptation to market changes and longer-horizon lesson extraction. The agent is tool-augmented, incorporating established trading strategies and expert knowledge, and emphasizes reasoning transparency.
Evaluation spans six datasets across stocks and cryptocurrency against nine baselines; the authors report average profit improvements above 36%, including a 92.27% return on one dataset. Published at KDD 2024 (doi:10.1145/3637528.3671801); the first author’s official implementation is at DVampire/FinAgent (MIT).
trading [●●●··] moderate ai [●●●●·] advanced programming [●····] none setup [●····] none
extended by AgenticTrading · Can LLM-based Financial Investing Strategies Outperform the Market in Long Run? · From Deep Learning to LLMs: A Survey of AI in Quantitative Investment · FINSABER
athenara:~$