QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model
This addresses the problem of efficiently integrating domain-specific knowledge for autonomous agents in quantitative investment, representing an incremental improvement in a specialized domain.
The paper tackles the challenge of building autonomous agents for quantitative investment by introducing a two-loop framework that refines responses and updates a knowledge base, enabling the agent to progressively approximate optimal behavior with provable efficiency. Empirical results show QuantAgent uncovers viable financial signals and enhances forecast accuracy.
Autonomous agents based on Large Language Models (LLMs) that devise plans and tackle real-world challenges have gained prominence.However, tailoring these agents for specialized domains like quantitative investment remains a formidable task. The core challenge involves efficiently building and integrating a domain-specific knowledge base for the agent's learning process. This paper introduces a principled framework to address this challenge, comprising a two-layer loop.In the inner loop, the agent refines its responses by drawing from its knowledge base, while in the outer loop, these responses are tested in real-world scenarios to automatically enhance the knowledge base with new insights.We demonstrate that our approach enables the agent to progressively approximate optimal behavior with provable efficiency.Furthermore, we instantiate this framework through an autonomous agent for mining trading signals named QuantAgent. Empirical results showcase QuantAgent's capability in uncovering viable financial signals and enhancing the accuracy of financial forecasts.