Skip to content
All library documents

TiMi: Separating Trading Strategy Design from Minute-Level Deployment

Article arXiv papers · Author: Zifan Song et al.
Read the original

Summary

The document introduces TiMi, a multi-agent system for quantitative trading that separates the development of a trading strategy from its minute-level execution. It assigns language models specialized tasks such as interpreting market information, programming trading bots, and mathematical reasoning. Its process moves from broad market patterns to strategy customization, then uses a feedback loop to refine and deploy the resulting policy.

The paper reports evaluations across more than 200 stock and cryptocurrency trading pairs, claiming stable profitability, efficient actions, and risk control in volatile markets. The summary provides no performance figures, comparison methods, or details about data selection, transaction costs, or out-of-sample testing. Those omissions make it difficult to judge how robust the results are or how well the system would transfer to live trading.

Key ideas

  • TiMi separates strategy development from minute-level deployment.
  • The system assigns language models roles in semantic analysis, programming, and mathematical reasoning.
  • Its analytical workflow moves from broad market patterns to customized strategies.
  • A mathematical feedback loop is used to refine trading policies.
  • The paper reports evaluations across stock and cryptocurrency pairs but gives limited information about their design.

Tags

Machine learningExecutionCryptoEquities
Full text
# Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading


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









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.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.