Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents

TL;DR

This paper introduces a new ToM-based dialogue task and dataset, along with a reasoning framework that improves large language models' ability to infer mental states and persuasive strategies in conversations.

Contribution

It presents a novel ToM-PD task, a large annotated dataset ToM-BPD, and a knowledge-enhanced reasoning framework TTBYS that enhances LLMs' mental state inference in persuasive dialogues.

Findings

Qwen3-8B with TTBYS outperforms GPT-5 in predicting mental states and strategies.

The approach improves interpretability and reasoning consistency.

Experimental results show significant performance gains.

Abstract

Persuasive dialogue requires reasoning about others' latent mental states, a capability known as Theory of Mind (ToM). However, due to reliance on simple prompting strategies and insufficient ToM knowledge, existing LLMs often fail to capture the intrinsic dependencies among mental states, leading to fragmented representations and unstable reasoning. To address these challenges, we introduce the ToM-based Persuasive Dialogue (ToM-PD) task, grounded in the Belief-Desire-Intention (BDI) framework, which explicitly models the sequential dependencies among mental states in multi-turn dialogues. To facilitate research on this task, we construct a large-scale annotated dataset, ToM-based Broad Persuasive Dialogues (ToM-BPD), capturing fine-grained mental states and corresponding persuasive strategies. We further propose Think Thrice Before You Speak (TTBYS), a knowledge-enhanced stepwise reasoning framework that leverages both explicit and implicit prior experiences to improve LLMs' inference of desires, beliefs, and persuasive strategies. Experimental results demonstrate that Qwen3-8B equipped with TTBYS outperforms GPT-5 by 1.20%, 22.80%, and 16.97% in predicting desires, beliefs, and persuasive strategies, respectively. Case studies further show that our approach enhances interpretability and consistency in reasoning.