{"work":{"id":"01508be0-d975-4ff6-8045-1e0b229fbab4","openalex_id":"https://openalex.org/W4387293261","doi":"10.48550/arxiv.2309.16797","arxiv_id":"2309.16797","raw_key":null,"title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","authors":null,"authors_text":"Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, Tim Rockt\\\"aschel","year":2023,"venue":"cs.CL","abstract":"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.","external_url":"https://arxiv.org/abs/2309.16797","cited_by_count":27,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2309.16797","created_at":"2026-05-09T22:49:16.099006+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","render_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution"},"hub":{"state":{"work_id":"01508be0-d975-4ff6-8045-1e0b229fbab4","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":50,"external_cited_by_count":27,"distinct_field_count":11,"first_pith_cited_at":"2023-09-07T00:07:15+00:00","last_pith_cited_at":"2026-07-01T17:57:03+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T04:09:33.102666+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":8}],"polarity_counts":[{"context_polarity":"background","n":7},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}