MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914031134048256 |
|---|---|
| author | Chen, Yang Jiang, Yueheng Ma, Zhaozhao Cao, Yuchen Keung, Jacky Kuang, Kun Gan, Leilei Wu, Yiquan Wu, Fei |
| author_facet | Chen, Yang Jiang, Yueheng Ma, Zhaozhao Cao, Yuchen Keung, Jacky Kuang, Kun Gan, Leilei Wu, Yiquan Wu, Fei |
| contents | The inherent non-stationarity of financial markets and the complexity of multi-modal information pose significant challenges to existing quantitative trading models. Traditional methods relying on fixed structures and unimodal data struggle to adapt to market regime shifts, while large language model (LLM)-driven solutions - despite their multi-modal comprehension - suffer from static strategies and homogeneous expert designs, lacking dynamic adjustment and fine-grained decision mechanisms. To address these limitations, we propose MM-DREX: a Multimodal-driven, Dynamically-Routed EXpert framework based on large language models. MM-DREX explicitly decouples market state perception from strategy execution to enable adaptive sequential decision-making in non-stationary environments. Specifically, it (1) introduces a vision-language model (VLM)-powered dynamic router that jointly analyzes candlestick chart patterns and long-term temporal features to allocate real-time expert weights; (2) designs four heterogeneous trading experts (trend, reversal, breakout, positioning) generating specialized fine-grained sub-strategies; and (3) proposes an SFT-RL hybrid training paradigm to synergistically optimize the router's market classification capability and experts' risk-adjusted decision-making. Extensive experiments on multi-modal datasets spanning stocks, futures, and cryptocurrencies demonstrate that MM-DREX significantly outperforms 15 baselines (including state-of-the-art financial LLMs and deep reinforcement learning models) across key metrics: total return, Sharpe ratio, and maximum drawdown, validating its robustness and generalization. Additionally, an interpretability module traces routing logic and expert behavior in real time, providing an audit trail for strategy transparency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05080 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading Chen, Yang Jiang, Yueheng Ma, Zhaozhao Cao, Yuchen Keung, Jacky Kuang, Kun Gan, Leilei Wu, Yiquan Wu, Fei Trading and Market Microstructure The inherent non-stationarity of financial markets and the complexity of multi-modal information pose significant challenges to existing quantitative trading models. Traditional methods relying on fixed structures and unimodal data struggle to adapt to market regime shifts, while large language model (LLM)-driven solutions - despite their multi-modal comprehension - suffer from static strategies and homogeneous expert designs, lacking dynamic adjustment and fine-grained decision mechanisms. To address these limitations, we propose MM-DREX: a Multimodal-driven, Dynamically-Routed EXpert framework based on large language models. MM-DREX explicitly decouples market state perception from strategy execution to enable adaptive sequential decision-making in non-stationary environments. Specifically, it (1) introduces a vision-language model (VLM)-powered dynamic router that jointly analyzes candlestick chart patterns and long-term temporal features to allocate real-time expert weights; (2) designs four heterogeneous trading experts (trend, reversal, breakout, positioning) generating specialized fine-grained sub-strategies; and (3) proposes an SFT-RL hybrid training paradigm to synergistically optimize the router's market classification capability and experts' risk-adjusted decision-making. Extensive experiments on multi-modal datasets spanning stocks, futures, and cryptocurrencies demonstrate that MM-DREX significantly outperforms 15 baselines (including state-of-the-art financial LLMs and deep reinforcement learning models) across key metrics: total return, Sharpe ratio, and maximum drawdown, validating its robustness and generalization. Additionally, an interpretability module traces routing logic and expert behavior in real time, providing an audit trail for strategy transparency. |
| title | MM-DREX: Multimodal-Driven Dynamic Routing of LLM Experts for Financial Trading |
| topic | Trading and Market Microstructure |
| url | https://arxiv.org/abs/2509.05080 |