AMPO: Automatic Multi-Branched Prompt Optimization

Yurong Wu

Abstract:

Prompt engineering is very important to en-
hance the performance of large language mod-
els (LLMs). When dealing with complex is-
sues, human experts tend to distill multiple
patterns from data and inject relevant solutions
to optimize the prompts, achieving satisfying
results. However, existing automatic prompt
optimization techniques are only limited to
producing single flow instructions, struggling
with handling diverse patterns. In this paper,
we present AMPO, an automatic prompt opti-
mization method that can iteratively develop a
multi-branched prompt using failure cases as
feedback. Our goal is to explore a novel way
of structuring prompts with multi-branches
to better handle multiple patterns in complex
tasks, for which we introduce three modules:
Pattern Recognition, Branch Adjustment, and
Branch Pruning. In experiments across five
tasks, AMPO consistently achieves the best re-
sults. Additionally, our approach demonstrates
significant optimization efficiency due to our
adoption of a minimal search strategy.