QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

Paper: arXiv 2602.07085

Authors: Jun Han, Shuo Zhang, Wei Li, Zhi Yang, Yifan Dong, Tu Hu, Jialuo Yuan, Xiaomin Yu, Yumo Zhu, Fangqi Lou, Xin Guo, Zhaowei Liu, Tianyi Jiang, Ruichuan An, Jingping Liu, Biao Wu, Rongze Chen, Kunyi Wang, Yifan Wang, Sen Hu, Xinbing Kong, Liwen Zhang, Ronghao Chen, Huacan Wang

Abstract

Financial markets are noisy and non-stationary, making alpha mining highly sensitive to noise in backtesting results and sudden market regime shifts. While recent agentic frameworks improve alpha mining automation, they often lack controllable multi-round search and reliable reuse of validated experience. To address these challenges, we propose QuantaAlpha, an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory and improves factors through trajectory-level mutation and crossover operations. QuantaAlpha localizes suboptimal steps in each trajectory for targeted revision and recombines complementary high-reward segments to reuse effective patterns, enabling structured exploration and refinement across mining iterations. During factor generation, QuantaAlpha enforces semantic consistency across the hypothesis, factor expression, and executable code, while constraining the complexity and redundancy of the generated factor to mitigate crowding. Extensive experiments on the China Securities Index 300 (CSI 300) demonstrate consistent gains over strong baseline models and prior agentic systems. When utilizing GPT-5.2, QuantaAlpha achieves an Information Coefficient (IC) of 0.1501, with an Annualized Rate of Return (ARR) of 27.75% and a Maximum Drawdown (MDD) of 7.98%. Moreover, factors mined on CSI 300 transfer effectively to the China Securities Index 500 (CSI 500) and the Standard & Poor’s 500 Index (S&P 500), delivering 160% and 137% cumulative excess return over four years, respectively, which indicates strong robustness of QuantaAlpha under market distribution shifts.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 8.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: QuantaAlpha presents a novel trajectory-level evolutionary framework for LLM-driven alpha mining that addresses semantic drift and local search limitations in quantitative factor research. The paper features comprehensive empirical validation across multiple indices (CSI 300, CSI 500, S&P 500) with strong performance metrics and includes code repository links for reproducibility.

Research Flowchart

  flowchart TD
    A[Research Goal: Mining Robust, Low-Redundancy Financial Alphas via Evolutionary LLM Framework] --> B[(Inputs: CSI 300 Market Data & LLM - GPT-5.2)]
    
    B --> C[QuantaAlpha Framework: Trajectory-Based Evolutionary Search]
    
    subgraph C [QuantaAlpha Core Methodology]
        C1[End-to-End Mining Trajectories] --> C2[Localization & Targeted Mutation of Suboptimal Steps]
        C1 --> C3[Recombination / Crossover of High-Reward Segments]
        C2 & C3 --> C4[Constrained Generation: Semantic Consistency & Complexity Control]
    end

    C --> D[Backtesting & Cross-Market Transferability Evaluation]

    D --> E[Key Outcomes: High In-Market Performance & Robust Cross-Market Transfer]

    subgraph E [Results & Findings]
        E1[CSI 300 Performance: IC 0.1501 | ARR 27.75% | MDD 7.98%]
        E2[Out-of-Distribution Cumulative Excess Return: CSI 500 +160% | S&P 500 +137%]
    end

Cited References (37)

1. Can chatgpt forecast stock price movements? return predictability and large language models — → 2304.07619
2. A multimodal foundation agent for financial trading: Tool-augmented, diversified, and generalist (2024)
3. Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2025) — link
4. Tradingagents: Multi-agents llm financial trading framework — → 2412.20138
5. AlphaAgent: LLM-driven alpha mining with regularized exploration to counteract alpha decay (2025)
6. R&D-Agent-Quant: a multi-agent framework for data-centric factors and model joint optimization — → 2505.15155
7. Alphaforge: A framework to mine and dynamically combine formulaic alpha factors (2025)
8. Alphafin: Benchmarking financial analysis with retrieval-augmented stock-chain framework (2024)

6 of 37 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.