Paper: arXiv 2507.17211

Authors: Haochen Luo, Yuan Zhang, Chen Liu

Abstract

Sparse portfolio optimization is a fundamental yet challenging problem in quantitative finance, since traditional approaches heavily relying on historical return statistics and static objectives can hardly adapt to dynamic market regimes. To address this issue, we propose Evolutionary Factor Search (EFS), a novel framework that leverages large language models (LLMs) to automate the generation and evolution of alpha factors for sparse portfolio construction. By reformulating the asset selection problem as a top-m ranking task guided by LLM-generated factors, EFS incorporates an evolutionary feedback loop to iteratively refine the factor pool based on performance. Extensive experiments on five Fama-French benchmark datasets and three real-market datasets (US50, HSI45 and CSI300) demonstrate that EFS significantly outperforms both statistical-based and optimization-based baselines, especially in larger asset universes and volatile conditions. Comprehensive ablation studies validate the importance of prompt composition, factor diversity, and LLM backend choice. Our results highlight the promise of language-guided evolution as a robust and interpretable paradigm for portfolio optimization under structural constraints.

Complexity vs Empirical Score

  • Math Complexity: 6.5/10
  • Empirical Rigor: 6.0/10 (capped from 7.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces a novel evolutionary framework combining LLM generation with rigorous backtesting on multiple real-market datasets, though the mathematical depth is moderate (combining ranking theory with evolutionary algorithms) rather than exceptionally advanced.

Research Flowchart

  flowchart TD
  A["Research Goal: Enhance Sparse Portfolio Optimization with LLM-Generated Factors"] --> B["Data Collection & Setup"]
  
  B --> C["Core Methodology: Evolutionary Factor Search EFS"]
  
  subgraph C ["EFS Framework"]
      C1["LLM Prompt Engineering<br>Initial Factor Generation"]
      C2["Factor Evaluation<br>Top-m Ranking Performance"]
      C3["Evolutionary Loop<br>Selection & Mutation"]
  end
  
  B --> D["Baselines & Benchmarks<br>Fama-French + Market Datasets"]
  
  C --> E["Computational Process<br>Iterative Refinement"]
  
  E --> F["Key Findings & Outcomes"]
  
  subgraph F ["Results"]
      F1["Outperforms Statistical & Optimization Baselines"]
      F2["Scales Well with Large Asset Universes"]
      F3["Robust in Volatile Market Conditions"]
      F4["Validated via Ablation Studies"]
  end

Cited References (58)

  1. Short-term sparse portfolio optimization based on alternating direction method of multipliers (2018)
  2. A survey of large language models for financial applications: Progress, prospects and challenges — → 2406.11903
  3. Revolutionizing Finance with LLMs: An Overview of Applications and Insights (2024) — link
  4. Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Alpha Factor Mining (2026) — link
  5. A lpha F in: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework (2024) — link
  6. Constructing optimal sparse portfolios using regularization methods (2015)
  7. Qlib: An AI-oriented Quantitative Investment Platform (2020) — link
  8. The Markowitz contribution to portfolio theory (1979)
and 50 more
  1. Asset management: A systematic approach to factor investing (2014)
  2. Incorporating global industrial classification standard into portfolio allocation: A simple factor-based large covariance matrix estimator with high-frequency data (2016)
  3. A generalized approach to sparse and stable portfolio optimization problem (2018)
  4. Sparse and stable Markowitz portfolios (2009)
  5. Sparse index tracking with $K$-sparsity or $\epsilon$-deviation constraint via $\ell_0$-norm minimization (2022)
  6. Sparse portfolio selection via the sorted $\ell_1$-Norm (2020)
  7. A brief review of portfolio optimization techniques (2023)
  8. Autonomous Sparse Mean- CV a R Portfolio Optimization (2024) — link
  9. AutoAlpha: an Efficient Hierarchical Evolutionary Algorithm for Mining Alpha Factors in Quantitative Investment (2020) — link
  10. Generating synergistic formulaic alpha collections via reinforcement learning — → 2306.12964
  11. Mathematical discoveries from program search with large language models (2024) — link
  12. Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model (2024) — link
  13. Toward automated algorithm design: A survey and practical guide to meta-black-box-optimization (2025)
  14. ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution (2024)
  15. Multi-Objective Evolution of Heuristic Using Large Language Model (2025) — link
  16. Discovering Preference Optimization Algorithms with and for Large Language Models (2024)
  17. Perspective reformulations of mixed integer nonlinear programs with indicator variables (2010)
  18. F in T ral: A Family of GPT -4 Level Multimodal Financial Large Language Models (2024) — link
  19. Temporal data meets LLM–explainable financial time series forecasting — → 2306.11025
  20. Harnessing LLM s for Temporal Data - A Study on Explainable Financial Time Series Forecasting (2023) — link
  21. FinCon : A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making (2024)
  22. Active portfolio management (2000)
  23. A Globally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization (2024) — link
  24. AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay (2025) — link
  25. AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors (2025) — link
  26. Production of US RM-RF , SMB , and HML in the Fama-French Data Library (2023)
  27. Alpha- GPT : Human-AI Interactive Alpha Mining for Quantitative Investment (2025) — link
  28. Alpha-GPT 2.0: Human-in-the-Loop AI for Quantitative Investment (2024) — link
  29. LLMF actor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction (2024) — link
  30. GPT -Signal: Generative AI for Semi-automated Feature Engineering in the Alpha Research Process (2024) — link
  31. Can Large Language Models Mine Interpretable Financial Factors More Effectively? A Neural-Symbolic Factor Mining Agent Model (2024) — link
  32. 101 Formulaic Alphas (2016) — link
  33. Alpha191 (2024) — link
  34. GPT-4 Technical Report (2024) — link
  35. DeepSeek-V3 Technical Report (2025) — link
  36. Algorithm Evolution Using Large Language Model (2023) — link
  37. LightGBM : A Highly Efficient Gradient Boosting Decision Tree (2017)
  38. XGBoost : A Scalable Tree Boosting System (2016) — link
  39. Distribution of eigenvalues for some sets of random matrices (1967)
  40. A well-conditioned estimator for large-dimensional covariance matrices (2004)
  41. Noise dressing of financial correlation matrices (1999)
  42. Cleaning large correlation matrices: tools from random matrix theory (2017)
  43. The New Quant: A Survey of Large Language Models in Financial Prediction and Trading — → 2510.05533
  44. Large Language Model Agents in Finance: A Survey (2025)
  45. QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining — → 2602.07085
  46. Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2025) — link
  47. Trading-R1: Financial Trading with LLM Reasoning via Reinforcement Learning — → 2509.11420
  48. AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions — → 2508.11152
  49. HedgeAgents: A Balanced-aware Multi-agent Financial Trading System (2025) — link
  50. Alphabench: Benchmarking large language models in formulaic alpha factor mining (2026)

7 of 58 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.