简单迭代优化提示词，效果媲美复杂搜索方法。
Naive Prompt Optimization: Rethinking the Need for Complex Prompt Search
- 用教师模型反馈迭代修改提示词，流程简洁高效。
- 仅需较少采样次数，性能接近甚至超越复杂优化器GEPA。
- 优化后提示词可跨模型复用，尤其同家族模型效果好。
在多样化任务中高效提升自主代理性能，是加速智能体人工智能递归自我改进（RSI）的关键。提示词优化作为一种新兴方法，可在降低计算成本的同时实现接近微调模型权重的性能提升。然而，当前趋势日益趋向不必要的复杂化优化器设计。本文提出轻量级单线性方法Naive Prompt Optimization（NPO），通过教师模型与回溯反馈迭代修订提示词。NPO在较少采样次数下表现可比或优于GEPA，且随着教师模型能力增强，优势更明显，表明强教师推理能力可部分替代优化器侧的搜索复杂度。在交互式游戏中，NPO整体竞争力与GEPA相当，而GRPO在某些不适宜提示优化的任务上表现更优。此外，经NPO优化的提示词在其他学生模型上直接应用时亦能带来相似性能提升，尤其在同模型家族内效果显著。初步结果表明，简单的线性提示优化已可媲美复杂得多的搜索流程。
原文摘要 · Abstract (English)
Efficiently improving autonomous agents across diverse tasks is central to accelerating recursive self-improvement (RSI) in agentic AI, with prompt optimization emerging as a promising approach capable of delivering performance gains comparable to those achieved by fine-tuning model weights, while reducing computational costs in both optimization and serving. However, recent developments increasingly favor unnecessarily complex prompt optimizers. We introduce Naive Prompt Optimization (NPO), a lightweight single-lineage method that iteratively revises prompts using a teacher model with rollout feedback. NPO achieves comparable or better performance than GEPA with fewer rollouts, and its advantage increases with stronger teacher models, suggesting that stronger teacher reasoning can partially substitute for optimizer-side search complexity. In interactive games, NPO remains broadly competitive with GEPA, while GRPO performs better on some tasks less amenable to prompt optimization. We also show that NPO-optimized prompts elicit similar performance improvements when applied verbatim to other student models, especially across models within the same family. Overall, our preliminary results show that simple, linear prompt optimization can rival substantially more sophisticated and complex search procedures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。