This September 2025 paper describes QuantAgent, a novel multi-agent large language model (LLM) framework designed for high-frequency quantitative trading based solely on price-derived market signals. The system decomposes trading decisions into four specialized agents—IndicatorAgent, PatternAgent, TrendAgent, and DecisionAgent—which analyze market dynamics from complementary perspectives and communicate through structured prompts. QuantAgent consistently outperforms baseline models across diverse assets, including commodities, equities, and cryptocurrencies, demonstrating robust generalization and achieving high directional accuracy in predicting price movements. A key feature is its ability to produce traceable, language-native explanations for its trading decisions, enhancing transparency and interpretability in a field traditionally marked by opaque algorithms. The framework also includes a local, browser-based interface that allows users to visualize market data and interact with LLM-generated analyses, emphasizing user control and understanding.

Source:

https://arxiv.org/pdf/2509.09995