Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
This work provides a lightweight, policy-based method for influencing multi-agent social simulations, though it is incremental in applying parameterization to prompts rather than introducing a new paradigm.
The authors tackled the problem of controlling LLM-based multi-agent dialogue without training by parameterizing prompts as actions, and demonstrated that this approach can influence dialogue dynamics across five conversational indicators in two public discussion scenarios.
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.