aiqbench analysis
MADS introduces a scalable multi-agent framework that generates persuasive dialogue data through self-play, effectively reducing reliance on human annotation and addressing cold-start challenges in training datasets. By simulating diverse user personas via personality signifiers, the system successfully enhanced small LLMs' conversion rates in real-world marketing scenarios, demonstrating practical utility for data-scarce applications.
MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
arXiv:2510.05124v3 Announce Type: replace-cross Abstract: 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.
Abstract: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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA)
arXiv:2510.05124 [cs.CL]
(or arXiv:2510.05124v3 [cs.CL] for this version)
Full text under the publisher's open licence · 156 words
Related coverage
MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents
arXiv · Oct 12, 2026
Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
arXiv · Sep 16, 2026
Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?
arXiv · Aug 31, 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026