Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts

TL;DR

This paper proposes a novel framework for influencing LLM-based multi-agent dialogues by parameterizing prompts as policies, enabling dynamic control of conversational behaviors without training.

Contribution

It introduces a policy-parameterized prompt approach that guides multi-agent dialogue dynamics, bridging prompt engineering with policy-based control in LLM systems.

Findings

Prompt parameterization effectively influences dialogue flow.

The framework improves responsiveness and stance shifting.

Experimental results validate the approach across scenarios.

Abstract

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.