DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents

Tianyi Zhang, Mousumi Das, Abrar Anwar, Jesse Thomason, David Traum


Abstract
Large Language Models (LLMs) often struggle with persuasion in high-stakes scenarios. People’s individual personalities and concerns require tailored strategies rather than a one-size-fits-all approach. To address this challenge, we focus on a fire-rescue scenario in which an operator must persuade a resident to evacuate as a high-stakes persuasion domain and propose Dialogue Policy Selection (DiPS), a Q-learning framework to dynamically select persuasion strategies adapted to the evolving conversational context. Specifically, we train a critic, trained to maximize the chance of evacuation success, to select a persuasion policy at each turn based on the resident’s recent utterances. We then evaluate DiPS against multiple baselines in both simulated and real human interactions. We find that DiPS achieves higher evacuation success than a zero-shot LLM and generic RAG-augmented approach.
Anthology ID:
2026.sigdial-1.27
Volume:
Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
August
Year:
2026
Address:
Atlanta, Georgia, USA
Editors:
Jinho D. Choi, Yun-Nung Chen, Kotaro Funakoshi, Ali Emami
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
385–402
Language:
URL:
https://aclanthology.org/2026.sigdial-1.27/
DOI:
Bibkey:
Cite (ACL):
Tianyi Zhang, Mousumi Das, Abrar Anwar, Jesse Thomason, and David Traum. 2026. DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 385–402, Atlanta, Georgia, USA. Association for Computational Linguistics.
Cite (Informal):
DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents (Zhang et al., SIGDIAL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.sigdial-1.27.pdf