AI RESEARCH
MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models
arXiv CS.AI
•
ArXi:2605.23007v1 Announce Type: cross We explore the application of LLM-driven algorithm optimization to several common tasks in quantitative finance. MadEvolve, a general-purpose algorithm optimization framework inspired by DeepMind's Alpha-Evolve, was recently developed to optimize algorithms in computational cosmology. Here we nstrate the utility of MadEvolve to optimize algorithmic trading strategies and alpha generation at the example of Bitcoin trading.