用可调提示词控制大模型对话行为，无需训练即可影响讨论进程。
Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
- 将提示词视为可参数化的动作，动态生成以影响对话
- 在两个公共议题场景中验证了对话流畅性提升
- 适合社会模拟、多智能体系统研究者使用
大型语言模型（LLMs）已成为多智能体系统的新范式。然而，现有基于LLM的多智能体行为研究依赖于临时提示，缺乏系统的策略视角。不同于强化学习，本文探究提示词作为动作是否可参数化，从而构建一个由状态-动作对组成的轻量级策略，无需训练即可影响对话行为。该框架将提示词视为由LLM执行的动作，并根据当前智能体状态，通过五个组件动态构造提示。为评估参数化控制的有效性，我们基于五项指标（响应性、反驳性、证据使用、不重复性、立场转变）测试对话流。在两个涉及公众议题的讨论场景中，使用不同驱动的LLM智能体进行实验，结果表明提示参数化能够有效影响对话动态。这说明策略化提示提供了一种简单而有效的对话过程调控机制，有助于推动多智能体系统向社会模拟方向发展。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have emerged as a new paradigm for multi-agent systems. However, existing research on the behaviour of LLM-based multi-agents relies on ad hoc prompts and lacks a principled policy perspective. Different from reinforcement learning, we investigate whether prompt-as-action can be parameterized so as to construct a lightweight policy which consists of a sequence of state-action pairs to influence conversational behaviours without training. Our framework regards prompts as actions executed by LLMs, and dynamically constructs prompts through five components based on the current state of the agent. To test the effectiveness of parameterized control, we evaluated the dialogue flow based on five indicators: responsiveness, rebuttal, evidence usage, non-repetition, and stance shift. We conduct experiments using different LLM-driven agents in two discussion scenarios related to the general public and show that prompt parameterization can influence the dialogue dynamics. This result shows that policy-parameterised prompts offer a simple and effective mechanism to influence the dialogue process, which will help the research of multi-agent systems in the direction of social simulation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。