# From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery

arXiv: https://arxiv.org/abs/2605.15412 · HTML: https://mlsanity.com/paper/2605.15412/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 86 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 30 of 59)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance](https://mlsanity.com/paper/2306.05443/) (2023)
- [ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering](https://mlsanity.com/paper/2210.03849/) (2022)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [FinBen: A Holistic Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2402.12659/) (2024)
- [InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning](https://mlsanity.com/paper/2309.13064/) (2023)
- [Impact of News on the Commodity Market: Dataset and Results](https://mlsanity.com/paper/2009.04202/) (2020)
- [Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis](https://mlsanity.com/paper/2305.07972/) (2023)
- [INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent](https://mlsanity.com/paper/2412.18174/) (2024)
- [ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts](https://mlsanity.com/paper/2210.12467/) (2022)
- [Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment](https://mlsanity.com/paper/2308.00016/) (2023)
- [AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework](https://mlsanity.com/paper/2403.12582/) (2024)
- [R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization](https://mlsanity.com/paper/2505.15155/) (2025)
- [AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay](https://mlsanity.com/paper/2502.16789/) (2025)
- [Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning](https://mlsanity.com/paper/2306.12964/) (2023)
- [FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models](https://mlsanity.com/paper/2402.10986/) (2024)
- [QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model](https://mlsanity.com/paper/2402.03755/) (2024)
- [A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models](https://mlsanity.com/paper/2508.08712/) (2025)
- [AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors](https://mlsanity.com/paper/2406.18394/) (2024)
- [When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments](https://mlsanity.com/paper/2407.18957/) (2024)
- [Empowering Many, Biasing a Few: Generalist Credit Scoring through Large Language Models](https://mlsanity.com/paper/2310.00566/) (2023)
- [FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting](https://mlsanity.com/paper/2502.18834/) (2025)
- [AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agents](https://mlsanity.com/paper/2504.06614/) (2025)
- [A Survey of AIOps in the Era of Large Language Models](https://mlsanity.com/paper/2507.12472/) (2025)

## Built on by (most cited first, 6 of 6)

- [AQuA: Recursively Self-Improving Quantitative Trading Research Agents](https://mlsanity.com/paper/2608.12841/) (2026)
- [AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search](https://mlsanity.com/paper/2608.11250/) (2026)
- [Agentic Empirical Asset Pricing: Methodological Foundations](https://mlsanity.com/paper/2609.00731/) (2026)
- [AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining](https://mlsanity.com/paper/2609.29014/) (2026)
- [Playing social deduction games with reinforcement fine-tuned large language models](https://mlsanity.com/paper/2610.04261/) (2026)
- [AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery](https://mlsanity.com/paper/2610.14959/) (2026)

## Abstract (arXiv)

Modern quantitative trading increasingly relies on systematic models to extract predictive signals from large-scale financial data, where alpha factor discovery plays a central role in transforming market observations into tradable signals. Recent LLM-based methods have shown promise in automating factor generation, but most of them still rely on prompt-level generation--evaluation--feedback loops for iterative optimization. As the loop becomes longer, repeatedly appended historical candidates and feedback can cause context explosion, increase inference cost, dilute useful information, and introduce feedback drift. Moreover, these methods often depend on very large LLMs whose stable generation preferences may lead to structurally similar expressions, redundant candidates, and search stagnation. To address these limitations, we propose textscQuantEvolver, a self-evolving alpha factor discovery framework based on reinforcement fine-tuning. Instead of accumulating feedback in the prompt, textscQuantEvolver converts executable quantitative evaluation into policy updates, enabling a Miner LLM to internalize historical optimization experience through parameter learning. Specifically, textscQuantEvolver constructs high-quality seed factors, builds diverse seed--time-window training tasks, generates executable Factor DSL expressions, evaluates them through Regime Backtest, and optimizes the Miner LLM with Diversity-Complementarity Reward. During training, high-quality factors are continuously accumulated in a Mined Factor Database, which serves as the final discovered factor library. Extensive experiments on three realistic market benchmarks demonstrate the effectiveness of textscQuantEvolver, which consistently improves the primary evaluation metric of each task over existing LLM-based alpha factor discovery baselines, produces higher-quality and more complementary factor pools.