@inproceedings{e6218064b90947b68d5d14fa5f331c71,
title = "MW-MAS: A Multi-agent System for Multimodal Watermarking with Agent Orchestration",
abstract = "Recent advances in generative models enabled the creation of high-quality synthetic text and images, raising concerns about provenance and misuse. We propose MW-MAS (Multimodal Watermarking Multi-Agent System), a unified framework that orchestrates watermarking across text and image modalities via three agents: the Text Watermark Agent, Image Watermark Agent, and Orchestration Agent. The Orchestration Agent adaptively selects optimal agent combinations based on sample characteristics. Evaluated on the WIT dataset, MW-MAS achieves up to 2× faster runtime than dual-agent baselines while maintaining high fidelity and robust bit-level watermark retrieval, offering a flexible and practical solution for multimodal content watermarking. Code is available at https://github.com/lynnchoi0126/MW-MAS.",
keywords = "Agent Orchestration, Multi-Agent Systems, Multi-modal Watermark",
author = "Lynn Choi and Minsu Park and Taeeun Kim and Eunil Park",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 26th International Conference on Principles and Practice of Multi-Agent Systems, PRIMA 2025 ; Conference date: 16-12-2025 Through 19-12-2025",
year = "2026",
doi = "10.1007/978-3-032-13562-9\_26",
language = "English",
isbn = "9783032135612",
series = "Lecture Notes in Computer Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "339--347",
editor = "Catalin Dima and Angelo Ferrando and Vadim Malvone",
booktitle = "PRIMA 2025",
}