Title: Self-Evolution of Large Language Models
Abstract: This talk explores the emerging concept of self-evolution in large language models (LLMs), where models self-evaluate, refine, and improve their reasoning capabilities over time with minimal human intervention. I will focus on the techniques behind self-improvement, including approaches such as bootstrapped reasoning, synthesising reasoning and acting, verbalised reinforcement learning, and LLM learning via self-play or self-planning. I will also discuss the challenges in the context of LLM self-evolution and conclude with an outlook for future research.