Generative AI Agents for Controllable and Protected Content Creation

Haris Khan, Sadia Asif

Track: Regular paper

Keywords: Generative AI, Multi-agent systems, Content protection, Controllability, Watermarking, Information retrieval

TL;DR: We present a multi-agent framework for generative AI that ensures controllability of outputs and embeds watermarking for secure provenance, enabling responsible and traceable creative workflows.

Abstract: The proliferation of generative AI has transformed creative workflows, yet current systems face critical challenges in controllability and content protection. We propose a novel multi-agent framework that addresses both limitations through specialized agent roles and integrated watermarking mechanisms. Unlike existing multi-agent systems focused solely on generation quality, our approach uniquely combines controllable content synthesis with provenance protection during the generation process itself. The framework orchestrates Director/Planner, Generator, Reviewer, Integration, and Protection agents with human-in-the-loop feedback to ensure alignment with user intent while embedding imperceptible digital watermarks. We formalize the pipeline as a joint optimization objective unifying controllability, semantic alignment, and protection robustness. This work contributes to responsible generative AI by positioning multi-agent architectures as a solution for trustworthy creative workflows with built-in ownership tracking and content traceability.

Submission Number: 24