Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading

2025-10-06

AI Summary

Existing financial trading agents predominantly rely on anthropomorphic modeling, which introduces affective biases, overdependence on peripheral information, and necessitates continuous online inference—compromising both strategic depth and mechanical rationality. This paper proposes TiMi, the first rationality-driven multi-agent quantitative trading system. TiMi decouples strategic generation from minute-level execution, establishing a two-tier analytical paradigm: “macro-pattern recognition → micro-customized optimization.” It employs hierarchical programming and mathematical reflection–driven closed-loop optimization, explicitly eschewing human role simulation. By synergistically integrating large language models’ capabilities in semantic understanding, code generation, and mathematical reasoning, TiMi achieves end-to-end strategy development, optimization, and deployment. Empirical evaluation across 200+ equities and cryptocurrency pairs demonstrates statistically significant improvements in profitability, execution efficiency, and risk control performance.

Technology Category

• Multiagent Systems: Modeling other Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Recent advancements in large language models (LLMs) and agentic systems have shown exceptional decision-making capabilities, revealing significant potential for autonomic finance. Current financial trading agents predominantly simulate anthropomorphic roles that inadvertently introduce emotional biases and rely on peripheral information, while being constrained by the necessity for continuous inference during deployment. In this paper, we pioneer the harmonization of strategic depth in agents with the mechanical rationality essential for quantitative trading. Consequently, we present TiMi (Trade in Minutes), a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment. TiMi leverages specialized LLM capabilities of semantic analysis, code programming, and mathematical reasoning within a comprehensive policy-optimization-deployment chain. Specifically, we propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection. Extensive evaluations across 200+ trading pairs in stock and cryptocurrency markets empirically validate the efficacy of TiMi in stable profitability, action efficiency, and risk control under volatile market dynamics.

Problem

• Develops rationality-driven agent system for quantitative trading
• Decouples strategy development from minute-level deployment execution
• Addresses emotional biases and continuous inference limitations

Innovation

• Rationality-driven multi-agent system for trading
• Decouples strategy development from deployment
• Uses LLM capabilities for semantic and mathematical analysis