FactorMiner: A Self-Evolving Agent with Skills and Experience Memory for Financial Alpha Discovery

2026-02-16

AI Summary

This work addresses the challenges in quantitative investing—namely, the vast search space, high redundancy, and difficulty in discovering novel signals—by proposing a lightweight, self-evolving agent framework. Built upon the Ralph Loop paradigm, the framework integrates modular skill tools with a structured experience memory mechanism, operating through a closed-loop process of retrieval, generation, evaluation, and refinement. It continuously accumulates successful patterns and failure constraints as memory priors to enable efficient, low-redundancy, and interpretable alpha factor generation. Evaluated on multi-asset, multi-market datasets, the approach constructs a high-quality, diverse, and competitive alpha factor library, significantly enhancing both the efficiency of factor discovery and out-of-sample generalization performance.

Technology Category

• Multiagent Systems: Adversarial Agents
• Machine Learning: Evolutionary Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Formulaic alpha factor mining is a critical yet challenging task in quantitative investment, characterized by a vast search space and the need for domain-informed, interpretable signals. However, finding novel signals becomes increasingly difficult as the library grows due to high redundancy. We propose FactorMiner, a lightweight and flexible self-evolving agent framework designed to navigate this complex landscape through continuous knowledge accumulation. FactorMiner combines a Modular Skill Architecture that encapsulates systematic financial evaluation into executable tools with a structured Experience Memory that distills historical mining trials into actionable insights (successful patterns and failure constraints). By instantiating the Ralph Loop paradigm -- retrieve, generate, evaluate, and distill -- FactorMiner iteratively uses memory priors to guide exploration, reducing redundant search while focusing on promising directions. Experiments on multiple datasets across different assets and Markets show that FactorMiner constructs a diverse library of high-quality factors with competitive performance, while maintaining low redundancy among factors as the library scales. Overall, FactorMiner provides a practical approach to scalable discovery of interpretable formulaic alpha factors under the"Correlation Red Sea"constraint.

Problem

• alpha factor mining
• search space
• redundancy
• quantitative investment
• interpretable signals

Innovation

• self-evolving agent
• modular skill architecture
• experience memory
• alpha factor mining
• Ralph Loop