Recently, there has been an increasing interest in automated prompt optimization based on reinforcement learning (RL). This approach offers important advantages, such as generating interpretable prompts and being compatible with black-box foundation models. However, the substantial prompt space size poses challenges for RL-based methods, often leading to suboptimal policy convergence. This paper introduces MultiPrompter, a new framework that views prompt optimization as a cooperative game between prompters which take turns composing a prompt together. Our cooperative prompt optimization effectively reduces the problem size and helps prompters learn optimal prompts. We test our method on the text-to-image task and show its ability to generate higher-quality images than baselines.
@article{arxiv.2310.16730,
title = {MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning},
author = {Dong-Ki Kim and Sungryull Sohn and Lajanugen Logeswaran and Dongsub Shim and Honglak Lee},
journal= {arXiv preprint arXiv:2310.16730},
year = {2023}
}