QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

• URL: http://arxiv.org/abs/2602.07085v1
• Date: Fri, 06 Feb 2026 08:08:04 GMT
• Title: QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining
• 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 summary: QuantaAlpha is an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory.<n> QuantaAlpha localizes suboptimal steps in each trajectory for targeted revision.<n>During factor generation, QuantaAlpha enforces semantic consistency across the hypothesis, factor expression, and executable code.
• Score: 24.756255119539347
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution [11.490182876149062]
  We introduce AlphaPROBE, a framework that reframes alpha mining as the strategic navigation of a Directed Acyclic Graph (DAG)<n>By modeling factors as nodes and evolutionary links as edges, AlphaPROBE treats the factor pool as a dynamic, interconnected ecosystem.<n>Our results confirm that leveraging global evolutionary topology is essential for efficient and robust automated alpha discovery.
  arXiv  Detail & Related papers  (2026-02-12T13:14:58Z)
• ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking [84.07076200941474]
  ArenaRL is a reinforcement learning paradigm that shifts from pointwise scalar scoring to intra-group relative ranking.<n>We construct an intra-group adversarial arena and devise a tournament-based ranking scheme to obtain stable advantage signals.<n>Experiments show that ArenaRL substantially outperforms standard RL baselines.
  arXiv  Detail & Related papers  (2026-01-10T08:43:07Z)
• From Memorization to Creativity: LLM as a Designer of Novel Neural-Architectures [48.83701310501069]
  Large language models (LLMs) excel in program synthesis, yet their ability to autonomously navigate neural architecture design-balancing reliability, performance, and structural novelty--remains underexplored.<n>We address this by placing a code-oriented LLM within a closed-loop synthesis framework, analyzing its evolution over 22 supervised fine-tuning cycles.
  arXiv  Detail & Related papers  (2026-01-06T13:20:28Z)
• Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning [28.326583684637853]
  Signal decay and regime shifts pose recurring challenges for data-driven investment strategies in non-stationary markets.<n>Existing factor-based methods typically reduce alphas to numerical time series, overlooking the semantic rationale that determines when a factor is economically relevant.<n>We propose Alpha-R1, an 8B- parameter reasoning model trained via reinforcement learning for context-aware alpha screening.
  arXiv  Detail & Related papers  (2025-12-29T14:50:23Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• AlphaEvolve: A coding agent for scientific and algorithmic discovery [63.13852052551106]
  We present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs.<n>AlphaEvolve orchestrates an autonomous pipeline of LLMs, whose task is to improve an algorithm by making direct changes to the code.<n>We demonstrate the broad applicability of this approach by applying it to a number of important computational problems.
  arXiv  Detail & Related papers  (2025-06-16T06:37:18Z)
• Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Factor Mining [8.53606484300001]
  This paper introduces a novel framework that integrates Large Language Models (LLMs) with Monte Carlo Tree Search (MCTS)<n>A key innovation is the guidance of MCTS exploration by rich, quantitative feedback from financial backtesting of each candidate factor.<n> Experimental results on real-world stock market data demonstrate that our LLM-based framework outperforms existing methods by mining alphas with superior predictive accuracy and trading performance.
  arXiv  Detail & Related papers  (2025-05-16T11:14:17Z)
• AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay [43.50447460231601]
  We propose AlphaAgent, an autonomous framework that integrates Large Language Models with ad hoc regularizations for mining decay-resistant alpha factors.<n>AlphaAgent consistently delivers significant alpha in Chinese CSI 500 and US S&P 500 markets over the past four years.<n> Notably, AlphaAgent showcases remarkable resistance to alpha decay, elevating the potential for yielding powerful factors.
  arXiv  Detail & Related papers  (2025-02-24T02:56:46Z)
• QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCE [5.560011325936085]
  Powerful deep learning methods for alpha factor mining lack interpretability, making them unacceptable in the risk-sensitive real markets.<n>Formulaic alpha factors are preferred for their interpretability, while the search space is complex and powerful explorative methods are urged.<n>Recently, a promising framework is proposed for generating alpha factors using deep reinforcement learning.
  arXiv  Detail & Related papers  (2024-09-08T15:57:58Z)
• AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors [14.80394452270726]
  This paper proposes a two-stage alpha generating framework AlphaForge, for alpha factor mining and factor combination.<n> Experiments conducted on real-world datasets demonstrate that our proposed model outperforms contemporary benchmarks in formulaic alpha factor mining.
  arXiv  Detail & Related papers  (2024-06-26T14:34:37Z)
• DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning [56.887047551101574]
  We present DS-Agent, a novel framework that harnesses large language models (LLMs) agent and case-based reasoning (CBR) In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which can flexibly capitalize on the expert knowledge from Kaggle. In the deployment stage, DS-Agent implements a low-resource deployment stage with a simplified CBR paradigm, significantly reducing the demand on foundational capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-02-27T12:26:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.