Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

By Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, Tim Rocktaschel. International Conference on Machine Learning, 2023

525 citations recorded by the source corpus.

Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the reasoning abilities of Large Language Models (LLMs) in various domains. However, such hand-crafted prompt-strategies are often sub-optimal. In this paper, we present Promptbreeder, a general-purpose self-referential self-improvement mechanism that evolves and adapts prompts for a given domain. Driven by an LLM, Promptbreeder mutates a population of task-prompts, and subsequently evaluates them for fitness on a training set. Crucially, the mutation of these task-prompts is governed by mutation-prompts that the LLM generates and improves throughout evolution in a self-referential way. That is, Promptbreeder is not just improving task-prompts, but it is also improving the mutationprompts that improve these task-prompts. Promptbreeder outperforms state-of-the-art prompt strategies such as Chain-of-Thought and Plan-and-Solve Prompting on commonly used arithmetic and commonsense reasoning benchmarks. Furthermore, Promptbreeder is able to evolve intricate task-prompts for the challenging problem of hate speech classification.

View Paper: https://www.semanticscholar.org/paper/7fe071ea76e49bc3e573beb53f07721630954247

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Quoc V. Le
2. Xinyun Chen
3. Hanxiao Liu
4. Yoshua Bengio
5. Renqian Luo
6. Mohit Bansal
7. Percy Liang
8. Xuezhi Wang

Citations in the corpus

• Empowering Biomedical Discovery with AI Agents (2024, unknown): “For instance, An agent’s ability to evolve and tailor its prompts in reaction to user inputs has been demonstrated in [69].”
• Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine (2023, result): “Concurrent with our study, recent works [35, 7] also find that foundation models write better prompts than experts do.”
• Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model (2024, unknown): “Evolutionary search has been adopted in both code generation (Liventsev et al., 2023; Ma et al., 2023; Lehman et al., 2024; Hemberg et al., 2024) and text generation (Guo et al., 2023b; Fernando et al., 2023; Xu et al., 2023a).”
• AlphaEvolve: A coding agent for scientific and algorithmic discovery (2025, unknown): “LLM-guided evolution has also been used to improve AI systems by enhancing LLM prompts [27] and searching over neural architectures [14, 73].”
• Large Language Models as Optimizers (2023, background): “Some concurrent works on prompt optimization propose meta-prompts that explicitly ask the LLM to perform mutation and crossovers of existing prompts (Fernando et al., 2023; Guo et al., 2023).”