Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Generation to Attribution: Music AI Agent Architectures for the Post-Streaming Era

Wonil Kim, Hyeongseok Wi, Seungsoon Park, Taejun Kim, Sangeun Keum, Keunhyoung Kim, Taewan Kim, Jongmin Jung, Taehyoung Kim, Gaetan Guerrero, Mael Le Goff, Julie Po, Dongjoo Moon, Juhan Nam, Jongpil Lee

TL;DR

The paper addresses attribution, rights-management, and economic-model challenges posed by Generative AI in music. It proposes a content-based Music AI Agent architecture built on BlockDB, Retrieval-Augmented Generation, multi-agent orchestration, and a real-time Attribution Layer to tie generation to provenance and settlements. Key contributions include granular block-level attribution, a scalable ingestion workflow for artist-contributed Blocks, and a session-based creative loop enabling real-time, transparent compensation. The framework advocates a post-streaming paradigm where music is a living, collaborative ecosystem rather than a static catalog, potentially improving equity and fan participation.

Abstract

Generative AI is reshaping music creation, but its rapid growth exposes structural gaps in attribution, rights management, and economic models. Unlike past media shifts, from live performance to recordings, downloads, and streaming, AI transforms the entire lifecycle of music, collapsing boundaries between creation, distribution, and monetization. However, existing streaming systems, with opaque and concentrated royalty flows, are ill-equipped to handle the scale and complexity of AI-driven production. We propose a content-based Music AI Agent architecture that embeds attribution directly into the creative workflow through block-level retrieval and agentic orchestration. Designed for iterative, session-based interaction, the system organizes music into granular components (Blocks) stored in BlockDB; each use triggers an Attribution Layer event for transparent provenance and real-time settlement. This framework reframes AI from a generative tool into infrastructure for a Fair AI Media Platform. By enabling fine-grained attribution, equitable compensation, and participatory engagement, it points toward a post-streaming paradigm where music functions not as a static catalog but as a collaborative and adaptive ecosystem.

From Generation to Attribution: Music AI Agent Architectures for the Post-Streaming Era

TL;DR

The paper addresses attribution, rights-management, and economic-model challenges posed by Generative AI in music. It proposes a content-based Music AI Agent architecture built on BlockDB, Retrieval-Augmented Generation, multi-agent orchestration, and a real-time Attribution Layer to tie generation to provenance and settlements. Key contributions include granular block-level attribution, a scalable ingestion workflow for artist-contributed Blocks, and a session-based creative loop enabling real-time, transparent compensation. The framework advocates a post-streaming paradigm where music is a living, collaborative ecosystem rather than a static catalog, potentially improving equity and fan participation.

Abstract

Generative AI is reshaping music creation, but its rapid growth exposes structural gaps in attribution, rights management, and economic models. Unlike past media shifts, from live performance to recordings, downloads, and streaming, AI transforms the entire lifecycle of music, collapsing boundaries between creation, distribution, and monetization. However, existing streaming systems, with opaque and concentrated royalty flows, are ill-equipped to handle the scale and complexity of AI-driven production. We propose a content-based Music AI Agent architecture that embeds attribution directly into the creative workflow through block-level retrieval and agentic orchestration. Designed for iterative, session-based interaction, the system organizes music into granular components (Blocks) stored in BlockDB; each use triggers an Attribution Layer event for transparent provenance and real-time settlement. This framework reframes AI from a generative tool into infrastructure for a Fair AI Media Platform. By enabling fine-grained attribution, equitable compensation, and participatory engagement, it points toward a post-streaming paradigm where music functions not as a static catalog but as a collaborative and adaptive ecosystem.
Paper Structure (29 sections, 5 figures)

This paper contains 29 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Background
  3. Generative Model
  4. Content-based RAG
  5. AI Agent Architecture containing Media Content
  6. Content-based Music AI Agent for Integrated Attribution
  7. Creator Contribution Workflow
  8. Interactive Generation and Real-time Attribution
  9. Discussion and Conclusion
  10. Transformation of Creative Practice
  11. AI Attribution
  12. Economic Models and Fan Participation
  13. Infrastructure and Copyright Integration
  14. Post-Streaming Outlook
  15. Music AI Agent Pipeline: Architecture and Workflow
  16. ...and 14 more sections

Figures (5)

  • Figure 1: Music rights across media shifts into the AI era.
  • Figure 2: The architecture of the proposed Music AI agent designed to ensure fair artist compensation through an automated attribution and royalty system.
  • Figure 3: The user interface for a Music AI Agent, showing how a song is built through session-based, interactive layering of musical stems (left), and how a user can then select a specific track to request further modifications (right).
  • Figure 4: This diagram shows a multi-agent AI's workflow for creating music, where it analyzes a user's prompt and audio files, retrieves a relevant sound Block from BlockDB, and uses various tools to generate new musical stems as a final output.
  • Figure 5: The user interface of dashboard for artists. The dashboard provides detailed analytics on how their individual music Blocks are being used and the revenue they are generating.