Face forgery detection faces a critical challenge: a persistent gap between offline benchmarks and real-world efficacy,which we attribute to the ecological invalidity of training data.This work introduces Agent4FaceForgery to address two fundamental problems: (1) how to capture the diverse intents and iterative processes of human forgery creation, and (2) how to model the complex, often adversarial, text-image interactions that accompany forgeries in social media. To solve this,we propose a multi-agent framework where LLM-poweredagents, equipped with profile and memory modules, simulate the forgery creation process. Crucially, these agents interact in a simulated social environment to generate samples labeled for nuanced text-image consistency, moving beyond simple binary classification. An Adaptive Rejection Sampling (ARS) mechanism ensures data quality and diversity. Extensive experiments validate that the data generated by our simulationdriven approach brings significant performance gains to detectors of multiple architectures, fully demonstrating the effectiveness and value of our framework.
@article{arxiv.2509.12546,
title = {Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection},
author = {Yingxin Lai and Zitong Yu and Jun Wang and Linlin Shen and Yong Xu and Xiaochun Cao},
journal= {arXiv preprint arXiv:2509.12546},
year = {2025}
}