Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
q-fin.TR, cs.AI, cs.CE, cs.LG
Submitted: 2025-12-29
Updated: 2026-09-07
Code: https://github.com/FinStep-AI/Alpha-R1
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- From Deep Learning to LLMs: A survey of AI in Quantitative Investment
- Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading
- AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining
- Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information
- Measuring Massive Multitask Language Understanding
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- LoRA: Low-Rank Adaptation of Large Language Models
- A Survey of Reinforcement Learning from Human Feedback
- FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design
- TradingGPT: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance
- FinGPT: Democratizing Internet-scale Data for Financial Large Language Models
- Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
- Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models
- BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark
- SimPO: Simple Preference Optimization with a Reference-Free Reward
- Training language models to follow instructions with human feedback
- Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models