Personality-Aware Reinforcement Learning for Persuasive Dialogue with LLM-Driven Simulation

TL;DR

This paper introduces a personality-aware reinforcement learning framework for persuasive dialogue agents that adapt strategies based on user personality, using LLM-driven simulation to improve policy effectiveness and generalization.

Contribution

It proposes a novel reinforcement learning approach integrating personality modeling, agenda-based strategy control, and LLM simulation for persuasive dialogue.

Findings

Personality conditioning enhances persuasion rewards.

LLM simulation improves generalization to new user behaviors.

Change-of-mind penalties reduce retractions and improve outcomes.

Abstract

Effective persuasive dialogue agents adapt their strategies to individual users, accounting for the evolution of their psychological states and intentions throughout conversations. We present a personality-aware reinforcement learning approach comprising three main modules: (1) a Strategy-Oriented Interaction Framework, which serves as an agenda-based strategy controller that selects strategy-level actions and generate responses via Maximal Marginal Relevance (MMR) retrieval to ensure contextual relevance, diversity, and scalable data generation; (2) Personality-Aware User Representation Learning, which produces an 81-dimensional mixed-type embedding predicted at each turn from recent exchanges and appended to the reinforcement learning state; and (3) a Dueling Double DQN (D3QN) model and Reward Prediction, in which the policy is conditioned on dialogue history and turn-level personality estimates and trained using a composite reward incorporating agreement intent, donation amount, and changeof-mind penalties. We use an agenda-based LLM simulation pipeline to generate diverse interactions, from which personality estimation is inferred from the generated utterances. Experiments on the PersuasionForGood (P4G) dataset augmented with simulated dialogues reveal three main findings: (i) turn-level personality conditioning improves policy adaptability and cumulative persuasion rewards; (ii) LLM-driven simulation enhances generalization to unseen user behaviors; and (iii) incorporating a change-of-mind penalty reduces post-agreement retractions while slightly improving donation outcomes. These results demonstrate that structured interaction, dynamic personality estimation, and behaviorally informed rewards together yield more effective persuasive policies.