MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Mingjin, Liu, Yu, Liu, Huayi, Ye, Xiang, Jiang, Chao, Zhang, Hongguang, Ruan, Yu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909836355043328
author Li, Mingjin
Liu, Yu
Liu, Huayi
Ye, Xiang
Jiang, Chao
Zhang, Hongguang
Ruan, Yu
author_facet Li, Mingjin
Liu, Yu
Liu, Huayi
Ye, Xiang
Jiang, Chao
Zhang, Hongguang
Ruan, Yu
contents We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven behaviors by leveraging personality signifiers such as Zodiac Signs and MBTI types, a Dialog Agent executing task-oriented persuasion strategies and an Optimization Agent evaluating and refining dialogue outcomes. We further validate its effectiveness through users' Chain-of-Attitude (CoA) modeling and dedicated LLMs' persuasion assessment. This approach enables low-cost generation of training data without human annotation, addressing key industry challenges such as lack of user data, cold-start evaluation difficulties, and prompt inefficiency. Applied to a real-world marketing scenario, MADS significantly improved the persuasion capacity of small LLMs, increasing the organic traffic conversion rate by 22.4% (from 1.83% to 2.24%) , demonstrating clear business value.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05124
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
Li, Mingjin
Liu, Yu
Liu, Huayi
Ye, Xiang
Jiang, Chao
Zhang, Hongguang
Ruan, Yu
Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Multiagent Systems
We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven behaviors by leveraging personality signifiers such as Zodiac Signs and MBTI types, a Dialog Agent executing task-oriented persuasion strategies and an Optimization Agent evaluating and refining dialogue outcomes. We further validate its effectiveness through users' Chain-of-Attitude (CoA) modeling and dedicated LLMs' persuasion assessment. This approach enables low-cost generation of training data without human annotation, addressing key industry challenges such as lack of user data, cold-start evaluation difficulties, and prompt inefficiency. Applied to a real-world marketing scenario, MADS significantly improved the persuasion capacity of small LLMs, increasing the organic traffic conversion rate by 22.4% (from 1.83% to 2.24%) , demonstrating clear business value.
title MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
topic Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Multiagent Systems
url https://arxiv.org/abs/2510.05124