From Monolithic to Modular: Segment-level Automatic Prompt Optimization

Researchers propose SAPO, a segment-level automatic prompt optimization method that decomposes prompts into role, context, tasks, and output format, achieving the best average score across SQuADv2, TweetEval, XSUM, CommonGen, and GSM8K on GPT-3.5-Turbo and GPT-4o-mini, outperforming baselines including APE, OPRO, EvoPrompt, GEPA, and StraGO.

arXiv:2608.11219v1 Announce Type: new Abstract: Automatic Prompt Optimization APO often rewrites prompts monolithically, which can improve one behavior while degrading others. We present SAPO, a segment-level APO method that decomposes prompts into role, context, tasks, and output format, then applies targeted improvements based on top-5 and bottom-5 examples. The optimization loop uses one LLM with static meta-prompts and structured outputs for segmentation, weakness analysis, and candidate generation. We describe a train/validation protocol and a two-stage generation process: 1 segment-level diagnosis and recommendation extraction, 2 candidate synthesis constrained by weak/strong segment signals. Using the evaluation setup across SQuADv2, TweetEval, XSUM, CommonGen, and GSM8K on GPT-3.5-Turbo and GPT-4o-mini, SAPO achieves the best average score against Zero-shot and strong APO baselines including APE, OPRO, EvoPrompt, GEPA, and StraGO.