AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt Optimization

2026-09-30

AI Summary

This study addresses the limited generalization in prompt optimization caused by feedback selection strategies that overlook model weaknesses. To this end, we propose a weakness-aware adaptive feedback allocation method. By integrating performance metrics with task structure for sample screening, our approach replaces only a single sample per iteration to precisely localize weaknesses while preserving contextual information, thereby enabling efficient reflective prompt optimization. Experiments across six benchmarks demonstrate that the proposed method achieves superior scores and converges to high-quality prompts more rapidly. Notably, on the SGD task, it surpasses full-budget baselines using only half the budget, significantly enhancing both the efficiency and robustness of prompt optimization.

Abstract

Prompt optimization improves the performance of language-model systems on downstream tasks by refining their prompts. Classical methods evaluate prompts on task examples and use the resulting feedback to guide prompt revisions through reflection. However, when feedback selection does not account for the prompt's weaknesses, these revisions may improve performance on selected examples without yielding broader task improvements. To address this issue, we propose AdaGEPA, an adaptive feedback-allocation method that uses the prompt's performance and task structure to select examples for the next prompt revision. Our method replaces at most one example in each feedback minibatch to target an identified weakness while preserving the remaining feedback context. Across our main experiments on six downstream benchmarks, AdaGEPA achieves higher mean validation scores than non-adaptive feedback selection under matched rollout budgets. AdaGEPA also finds high-performing prompts earlier across several tasks. In the initial Schema-Guided Dialogue (SGD) study, its half-budget prompts outperform the non-adaptive baseline's full-budget prompts in joint goal accuracy on new dialogues from services seen and unseen during search. Overall, our findings highlight the potential of adaptive feedback allocation to improve both the effectiveness and rollout-budget efficiency of reflective prompt optimization.

Problem

• Prompt Optimization
• Reflective Prompt Optimization
• Feedback Allocation
• Large Language Models

Innovation

• Adaptive Feedback Allocation
• Reflective Prompt Optimization
• Prompt Optimization
• Feedback Selection
• Budget Efficiency