Google DeepMind has launched AlphaEvolve, a new coding agent that uses large language models to evolve and optimize algorithms across computing and mathematics.
AlphaEvolve pairs model-generated code with automated evaluators to verify, score, and evolve high-performing solutions.
The system integrates prompt sampling, language model outputs, and program evaluation through an evolutionary algorithm framework.
AlphaEvolve has been used to optimize data center scheduling, hardware design, AI training workflows, and tackle algorithmic challenges in mathematics.