[2309.16797] Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution

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-…

Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution Chrisantha Fernando Dylan Banarse Henryk Michalewski Simon Osindero Tim Rocktäschel Google DeepMind {chrisantha,dylski,henrykm,osindero,rocktaschel}@google.com 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 prompt

related reading

• [2309.16797] Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutionarxiv.org
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• [2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiv.org
• 2402.07927arxiv.org
• [2412.06769] Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• Self-Adapting Language Modelsarxiv.org
• Training Large Language Models to Reason in a Continuous Latent Spacearxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org
• LLMs Can Self-Improvearxiv.org
• [2605.03907] Steer Like the LLM: Activation Steering that Mimics Promptingarxiv.org