Paper page - QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

Source: https://huggingface.co/papers/2509.09995 Published on Sep 12, 2025

Abstract

QuantAgent, a multi-agent LLM framework, excels in high-frequency trading by leveraging specialized agents for technical indicators, chart patterns, trends, and risk, outperforming existing neural and rule-based systems.

Recent advances inLarge Language Models(LLMs) have demonstrated impressive capabilities in financial reasoning and market understanding. Multi-agent LLM frameworks such asTradingAgentandFINMEMaugment these models to long-horizon investment tasks, leveraging fundamental and sentiment-based inputs for strategic decision-making. However, such systems are ill-suited for the high-speed, precision-critical demands ofHigh-Frequency Trading(HFT).HFTrequires rapid, risk-aware decisions based on structured, short-horizon signals, includingtechnical indicators,chart patterns, and trend-based features, distinct from the long-term semantic reasoning typical of traditional financial LLM applications. To this end, we introduce QuantAgent, the first multi-agent LLM framework explicitly designed for high-frequency algorithmic trading. The system decomposes trading into four specialized agents, Indicator, Pattern, Trend, and Risk, each equipped withdomain-specific toolsandstructured reasoningcapabilities to capture distinct aspects of market dynamics over short temporal windows. Inzero-shot evaluationsacross tenfinancial instruments, includingBitcoinandNasdaq futures, QuantAgent demonstrates superior performance in bothpredictive accuracyand cumulative return over 4-hour trading intervals, outperforming strong neural and rule-based baselines. Our findings suggest that combining structured financial priors with language-native reasoning unlocks new potential fortraceable,real-time decision systemsin high-frequency financial markets.

View arXiv pageView PDFProject pageGitHub2.5kautoAdd to collection

Get this paper in your agent:

hf papers read 2509\.09995

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2509.09995 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2509.09995 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2509.09995 in a Space README.md to link it from this page.

Collections including this paper26

Browse 26 collections that include this paper