Advancing mathematics research with generative AI (2511.07420v2)

Abstract: The main drawback of using generative AI models for advanced mathematics is that these models are not logical reasoning engines. However, LLMs, and their refinements, can pick up on patterns in higher mathematics that are difficult for humans to see. By putting the design of generative AI models to their advantage, mathematicians may use them as powerful interactive assistants that can carry out laborious tasks, generate and debug code, check examples, formulate conjectures and more. We discuss how generative AI models can be used to advance mathematics research. We also discuss their integration with Computer Algebra Systems and formal proof assistants such as Lean.