Saved in:
Bibliographic Details
Main Authors: Wu, Siyi, Wang, Junqiao, Guan, Zhaoyang, Zhao, Leyi, Song, Xinyuan, Ying, Xinyu, Yu, Dexu, Wang, Jinhao, Zhang, Hanlin, Pak, Michele, He, Yangfan, Xin, Yi, Wang, Jianhui, Shi, Tianyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.20474
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916956941058048
author Wu, Siyi
Wang, Junqiao
Guan, Zhaoyang
Zhao, Leyi
Song, Xinyuan
Ying, Xinyu
Yu, Dexu
Wang, Jinhao
Zhang, Hanlin
Pak, Michele
He, Yangfan
Xin, Yi
Wang, Jianhui
Shi, Tianyu
author_facet Wu, Siyi
Wang, Junqiao
Guan, Zhaoyang
Zhao, Leyi
Song, Xinyuan
Ying, Xinyu
Yu, Dexu
Wang, Jinhao
Zhang, Hanlin
Pak, Michele
He, Yangfan
Xin, Yi
Wang, Jianhui
Shi, Tianyu
contents Cryptocurrency trading is a challenging task requiring the integration of heterogeneous data from multiple modalities. Traditional deep learning and reinforcement learning approaches typically demand large training datasets and encode diverse inputs into numerical representations, often at the cost of interpretability. Recent progress in large language model (LLM)-based agents has demonstrated the capacity to process multi-modal data and support complex investment decision-making. Building on these advances, we present \textbf{MountainLion}, a multi-modal, multi-agent system for financial trading that coordinates specialized LLM-based agents to interpret financial data and generate investment strategies. MountainLion processes textual news, candlestick charts, and trading signal charts to produce high-quality financial reports, while also enabling modification of reports and investment recommendations through data-driven user interaction and question answering. A central reflection module analyzes historical trading signals and outcomes to continuously refine decision processes, and the system is capable of real-time report analysis, summarization, and dynamic adjustment of investment strategies. Empirical results confirm that MountainLion systematically enriches technical price triggers with contextual macroeconomic and capital flow signals, providing a more interpretable, robust, and actionable investment framework that improves returns and strengthens investor confidence.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20474
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading
Wu, Siyi
Wang, Junqiao
Guan, Zhaoyang
Zhao, Leyi
Song, Xinyuan
Ying, Xinyu
Yu, Dexu
Wang, Jinhao
Zhang, Hanlin
Pak, Michele
He, Yangfan
Xin, Yi
Wang, Jianhui
Shi, Tianyu
Trading and Market Microstructure
Computation and Language
Machine Learning
Cryptocurrency trading is a challenging task requiring the integration of heterogeneous data from multiple modalities. Traditional deep learning and reinforcement learning approaches typically demand large training datasets and encode diverse inputs into numerical representations, often at the cost of interpretability. Recent progress in large language model (LLM)-based agents has demonstrated the capacity to process multi-modal data and support complex investment decision-making. Building on these advances, we present \textbf{MountainLion}, a multi-modal, multi-agent system for financial trading that coordinates specialized LLM-based agents to interpret financial data and generate investment strategies. MountainLion processes textual news, candlestick charts, and trading signal charts to produce high-quality financial reports, while also enabling modification of reports and investment recommendations through data-driven user interaction and question answering. A central reflection module analyzes historical trading signals and outcomes to continuously refine decision processes, and the system is capable of real-time report analysis, summarization, and dynamic adjustment of investment strategies. Empirical results confirm that MountainLion systematically enriches technical price triggers with contextual macroeconomic and capital flow signals, providing a more interpretable, robust, and actionable investment framework that improves returns and strengthens investor confidence.
title MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading
topic Trading and Market Microstructure
Computation and Language
Machine Learning
url https://arxiv.org/abs/2507.20474