🏆 Accepted at EMNLP 2025 Findings

• 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 supporting and persuasion domains, demonstrating its consistent improvements over strong baselines.
• Furthermore, PRINCIPLES maintains its robustness across extended and more diverse evaluation settings.

You can run PRINCIPLES in two phases:

First, set MODE="train" in scripts/run_ours.sh and run:

bash scripts/run_ours.sh

Set MODE="test" in scripts/run_ours.sh and run:

bash scripts/run_ours.sh