# Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading

arXiv: https://arxiv.org/abs/2508.06312 · HTML: https://mlsanity.com/paper/2508.06312/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2025.

## Built on by (most cited first, 9 of 9)

- [Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance](https://mlsanity.com/paper/2601.13770/) (2026)
- [AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining](https://mlsanity.com/paper/2508.13174/) (2025)
- [Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2512.23515/) (2025)
- [AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution](https://mlsanity.com/paper/2602.11917/) (2026)
- [TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents](https://mlsanity.com/paper/2603.22567/) (2026)
- [AQuA: Recursively Self-Improving Quantitative Trading Research Agents](https://mlsanity.com/paper/2608.12841/) (2026)
- [MEME: Modeling the Evolutionary Modes of Financial Markets](https://mlsanity.com/paper/2602.11918/) (2026)
- [Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks](https://mlsanity.com/paper/2606.14386/) (2026)
- [Agentic Empirical Asset Pricing: Methodological Foundations](https://mlsanity.com/paper/2609.00731/) (2026)

## Abstract (arXiv)

Alpha factor mining is a fundamental task in quantitative trading, aimed at discovering interpretable signals that can predict asset returns beyond systematic market risk. While traditional methods rely on manual formula design or heuristic search with machine learning, recent advances have leveraged Large Language Models (LLMs) for automated factor discovery. However, existing LLM-based alpha mining approaches remain limited in terms of automation, generality, and efficiency. In this paper, we propose Chain-of-Alpha, a novel, simple, yet effective and efficient LLM-based framework for fully automated formulaic alpha mining. Our method features a dual-chain architecture, consisting of a Factor Generation Chain and a Factor Optimization Chain, which iteratively generate, evaluate, and refine candidate alpha factors using only market data, while leveraging backtest feedback and prior optimization knowledge. The two chains work synergistically to enable high-quality alpha discovery without human intervention and offer strong scalability. Extensive experiments on real-world A-share benchmarks demonstrate that Chain-of-Alpha outperforms existing baselines across multiple metrics, presenting a promising direction for LLM-driven quantitative research.