DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
Quick Answer
This paper shows that The DiPS framework utilizes Q-learning to dynamically select tailored persuasion strategies in high-stakes scenarios, achieving higher evacuation success rates than zero-shot LLMs and generic RAG-augmented methods.
Quick Take
Evaluated in fire-rescue contexts, DiPS adapts to individual resident responses, significantly improving outcomes in critical situations.
Key Points
- DiPS employs Q-learning for dynamic persuasion strategy selection.
- Framework tested in fire-rescue scenarios for evacuation success.
- Outperforms zero-shot and generic -augmented approaches.
- Critic model maximizes chances of successful resident evacuation.
- Adapts to individual resident responses for better outcomes.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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 this http URL 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.
| Comments: | Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2026) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.01557 [cs.CL] |
| (or arXiv:2607.01557v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.01557 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tianyi Zhang [view email]
[v1]
Thu, 2 Jul 2026 00:24:48 UTC (1,205 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.