p1: Better Prompt Optimization with Fewer Prompts

arXiv:2604.08801 · cs.LG, cs.CL · Submitted 2026-04-09 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-04-09

Updated: 2026-08-26

Code: https://github.com/huggingface/Math-Verify

Terminology

• Accuracy — 31× in this paper · explained in 1 episode
• Benchmark — 15× in this paper · explained in 2 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Core — 6× in this paper · explained in 2 episodes
• Generalization — 5× in this paper · explained in 13 episodes
• Large Language Model (LLM) — 4× in this paper · explained in 3 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Axioms — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Homogenization — 1× in this paper · explained in 2 episodes
• International Math Olympiad — 1× in this paper
• KL Regularization — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Meta-learning — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• PRL: Prompts from Reinforcement Learning
• UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
• Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
• Prompt Curriculum Learning for Efficient LLM Post-Training
• EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• PRewrite: Prompt Rewriting with Reinforcement Learning
• StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models
• Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
• Understanding R1-Zero-Like Training: A Critical Perspective
• Automatic Prompt Optimization with "Gradient Descent" and Beam Search
• Generalizing Verifiable Instruction Following
• POLCA: Stochastic Generative Optimization with LLM
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Qwen3 Technical Report
• One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts
• PromptBridge: Cross-Model Prompt Transfer for Large Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks