Paper: arXiv 2507.20474
Authors: Siyi Wu, Junqiao Wang, Zhaoyang Guan, Leyi Zhao, Xinyuan Song, Xinyu Ying, Dexu Yu, Jinhao Wang, Hanlin Zhang, Michele Pak, Yangfan He, Yi Xin, Jianhui Wang, Tianyu Shi
Abstract
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.
Complexity vs Empirical Score
- Math Complexity: 3.0/10
- Empirical Rigor: 2.5/10
- Quadrant: Philosophers — conceptual discussion, lower math and empirical scores
Why this score: The paper focuses on an applied LLM-agent system architecture and multi-modal data integration rather than deep mathematical theory, resulting in low math complexity. While it describes system components and ablation studies, it lacks detailed empirical data, backtest performance metrics, or reproducible code/datasets, giving it low empirical rigor.
Research Flowchart
flowchart TD
A["Research Goal:<br>Interpretable & Adaptive Financial Trading"] --> B["Multi-Modal Data Inputs<br>News / Candlesticks / Signals"]
B --> C["MountainLion Agent System<br>Coordinated LLM Agents"]
C --> D["Central Reflection Module<br>Historical Analysis & Refinement"]
D --> C
C --> E{"Dynamic Adjustment &<br>User Interaction"}
E --> C
C --> F["Investment Strategies &<br>Financial Reports"]
F --> G["Key Outcomes:<br>Improved Returns &<br>Investor Confidence"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes MountainLion, a multi-modal, multi-agent LLM-based system for cryptocurrency trading that integrates textual news, candlestick charts, and on-chain signals to generate and refine investment reports.
Source sentence
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.
Assumes
No explicit assumptions found in the text.
Data
- OHLC data market-prices unknown
Source sentence
Our system utilizes OHLC data (Sezer et al., 2020) across multiple granularities (1d, 1h, 5m), stored in a structured MySQL database for longitudinal forecasting (Kim and Shin, 2019).
- News data text-news unknown
Source sentence
... with modules for price forecasting and news-driven recommendations.
Costs
Unclear
Finds 4
- MountainLion yields a 28% improvement in investment decision accuracy compared to traditional single-dimension analyses. performance
Source sentence
dation indicated a 28% improvement in investment decision accuracy when investors utilized MountainLion’s comprehensive assessments versus traditional, singular-dimension analyses.
- GenAI integration improves short-term price prediction accuracy by 15% over baseline models. predictive-accuracy
Source sentence
GenAI integration improved short-term price prediction accuracy by 15% compared to baseline models.
- User engagement duration increases by 35% and platform adoption rises among novice investors. performance
Source sentence
Data showed a 35% increase in user engagement duration and a notable increase in platform adoption rates among novice investors, underscoring the effectiveness of its user‑centric design.
- Empirical evaluations confirm that MountainLion improves medium-term forecasting accuracy while enhancing transparency and adaptability. predictive-accuracy
Source sentence
Empirical evaluations confirm that MountainLion improves medium-term forecasting accuracy while enhancing transparency and adaptability.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 35 related papers). Coverage is partial, so this is neither replication nor refutation.
3 papers in the archive
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.