Controlling diversity in LLM-agent world simulations is essential for maintaining stability in structured tasks while enabling variation where creativity is needed. However, we observe that dialogue diversity declines significantly over long-term simulation. To investigate the role of prompt design in conversational diversity, we modularized the utterance generation prompt and found that reducing the given information leads to more diverse outputs. Based on this insight, we propose Adaptive Prompt Pruning (APP), a novel method that allows users to control diversity through a single parameter, lambda. APP dynamically prunes the utterance generation prompt based on their attention weights and is compatible with traditional diversity control techniques. We demonstrate that APP effectively controls output diversity through extensive experiments, and propose a method to balance the control trade-offs. Additionally, we provide an in-depth analysis to offer insights into optimizing diversity control in multi-agent simulation.
View on arXiv@article{chu2025_2412.21102,
title={ Exploring and Controlling Diversity in LLM-Agent Conversation },
author={ KuanChao Chu and Yi-Pei Chen and Hideki Nakayama },
journal={arXiv preprint arXiv:2412.21102},
year={ 2025 }
}