DiPS uses a trained critic to select persuasion policies via Q-learning in a fire-rescue evacuation task and reports higher success rates than zero-shot LLM or RAG baselines in both simulation and human trials.
Companion Publication of the 25th International Conference on Multimodal Interaction , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
DiPS uses a trained critic to select persuasion policies via Q-learning in a fire-rescue evacuation task and reports higher success rates than zero-shot LLM or RAG baselines in both simulation and human trials.