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

arXiv: https://arxiv.org/abs/2602.14670 · HTML: https://mlsanity.com/paper/2602.14670/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2026.

## Built on by (most cited first, 17 of 17)

- [AEL: Evolving Agent Harness in Open-Ended Environments](https://mlsanity.com/paper/2604.21725/) (2026)
- [Hubble: An LLM-Driven Agentic Framework for Safe, Diverse, and Reproducible Alpha Factor Discovery](https://mlsanity.com/paper/2604.09601/) (2026)
- [AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents](https://mlsanity.com/paper/2606.20625/) (2026)
- [AQuA: Recursively Self-Improving Quantitative Trading Research Agents](https://mlsanity.com/paper/2608.12841/) (2026)
- [X-Alpha: An AI Quant Researcher with Memory-Driven Self-Evolution](https://mlsanity.com/paper/2607.08332/) (2026)
- [EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading](https://mlsanity.com/paper/2607.12455/) (2026)
- [AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search](https://mlsanity.com/paper/2608.11250/) (2026)
- [SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data](https://mlsanity.com/paper/2608.28408/) (2026)
- [FORESIGHT-9: Prospective and Process-Aware Evaluation of Adaptive Trading Agents](https://mlsanity.com/paper/2608.29372/) (2026)
- [Agentic Empirical Asset Pricing: Methodological Foundations](https://mlsanity.com/paper/2609.00731/) (2026)
- [GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data](https://mlsanity.com/paper/2609.08719/) (2026)
- [AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining](https://mlsanity.com/paper/2609.29014/) (2026)
- [EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research](https://mlsanity.com/paper/2609.33524/) (2026)
- [From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining](https://mlsanity.com/paper/2609.35559/) (2026)
- [On the Boundary of Admission Gates: An Injected-Truth Study of Falsification-First Selection in Quantitative Strategy Research](https://mlsanity.com/paper/2610.07701/) (2026)
- [AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery](https://mlsanity.com/paper/2610.14959/) (2026)
- [EvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research](https://mlsanity.com/paper/2610.17130/) (2026)

## Abstract (arXiv)

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.