AlphaPilot: Multi-Turn Tool-Using LLM Agents for Adaptive Alpha Mining with Reinforcement Learning

arXiv:2610.15488 · cs.CL, cs.LG · Submitted 2026-10-11 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-10-11

Updated: 2026-10-11

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning
• Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
• AlphaEval: A Comprehensive and Efficient Evaluation Framework for Formula Alpha Mining
• AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution
• QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining
• Alpha-R1: Alpha Screening with LLM Reasoning via Reinforcement Learning
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
• Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
• FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
• Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
• Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance
• Alpha Mining and Enhancing via Warm Start Genetic Programming for Quantitative Investment
• HybridFlow: A Flexible and Efficient RLHF Framework
• AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors
• Trade-R1: Bridging Verifiable Rewards to Stochastic Environments via Process-Level Reasoning Verification
• AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay
• Mem-{\alpha}: Learning Memory Construction via Reinforcement Learning
• AlphaLogics: A Market Logic-Driven Multi-Agent System for Scalable and Interpretable Alpha Factor Generation
• BloombergGPT: A Large Language Model for Finance

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering