HAPO: Hyper-reflection for Automatic Prompt Optimization
Pending peer review from Preparing for IJCAI-2026, 2025
Abstract
An improvement of GEPA (automatic prompt optimization) through “hyper-reflection”, enabling compact LLMs to achieve performance closer to frontier models on complex tasks like SQL query equivalence generation and refutation.
Recommended citation: Lesner, J., & Yan, X. (2025). Preparing for IJCAI-2026.
Download Paper