PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents
This work addresses limitations in proactive dialogue agents for applications like emotional support and persuasion, offering an incremental improvement over existing methods.
The paper tackles the problem of strategy planning for proactive dialogue agents by proposing PRINCIPLES, a synthetic strategy memory derived from offline self-play simulations, which improves performance in emotional support and persuasion domains without additional training.
Dialogue agents based on large language models (LLMs) have shown promising performance in proactive dialogue, which requires effective strategy planning. However, existing approaches to strategy planning for proactive dialogue face several limitations: limited strategy coverage, preference bias in planning, and reliance on costly additional training. To address these, we propose PRINCIPLES: a synthetic strategy memory for proactive dialogue agents. PRINCIPLES is derived through offline self-play simulations and serves as reusable knowledge that guides strategy planning during inference, eliminating the need for additional training and data annotation. We evaluate PRINCIPLES in both emotional support and persuasion domains, demonstrating consistent improvements over strong baselines. Furthermore, PRINCIPLES maintains its robustness across extended and more diverse evaluation settings. See our project page at https://huggingface.co/spaces/kimnamssya/Principles.