SOURCE-LINKED INTELLIGENCE

ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Evolutionary prompt optimizers such as GEPA suffer from prompt bloat: each iteration appends rules and caveats, producing prompts up to 3$\times$ longer yet no more accurate. We trace this to three deficiencies - incomplete error observation, limited search diversity, and unreliable selection - and propose ESPO (Error-Structured Prompt Optimization), which decomposes prompt optimization into three phases: Diagnose clusters all training errors into structural patterns in one round; Propose generates candidates via four complementary strategies with independent biases; Select applies bootstrap s

Read original source ↗ Open in workspace

recordType

paper

region

Global