MA$^{2}$P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion

2026-05-18

AI Summary

This work addresses the challenge of strategic inconsistency and cross-domain instability in persuasive dialogue, which arises from the difficulty of accurately inferring a target’s internal beliefs and desires in complex persuasion scenarios. To overcome these limitations, the paper proposes the first multi-agent persuasion framework incorporating metacognitive mechanisms. The framework features a metacognitive configurator that dynamically selects appropriate meta-strategies from a structured knowledge base and coordinates modules for perception management, mental state reasoning, strategy execution, memory maintenance, and performance evaluation to achieve end-to-end strategically consistent persuasion. Experimental results demonstrate that the proposed approach significantly improves persuasion success rates and outperforms existing baselines.

Abstract

Persuasive dialogue generation plays a vital role in decision-making, negotiation, counseling, and behavior change, yet it remains a challenging problem. In complex persuasion where the persuadee's internal states are not expressed clearly, the persuader must interpret responses, infer the persuadee's latent mental states (e.g., beliefs and desires), and translate them into targeted, strategy-consistent actions; however, current approaches often produce generic or weakly grounded responses even when such cues are identified. Moreover, although large language models (LLMs) can generate persuasive content, their performance varies substantially across domains due to uneven knowledge coverage and limited reasoning generalization. To address these challenges, we propose MA$^{2}$P, a meta-cognitive autonomous intelligent agent framework for complex persuasion. Specifically, we develop an autonomous multi-agent architecture that coordinates perception management, mental-state inference, strategy execution, memory maintenance, and performance evaluation. To mitigate cross-domain performance variation, we further design a meta-cognitive configurator that selects an appropriate meta-strategy from a structured knowledge base at the outset, thereby guiding subsequent reasoning and planning. Experimental results show that our approach achieves a higher persuasion success rate than baselines.

Problem

• persuasive dialogue generation
• complex persuasion
• latent mental states
• large language models
• cross-domain performance

Innovation

• meta-cognitive
• autonomous intelligent agents
• mental-state inference
• persuasive dialogue
• multi-agent framework