Multi-Agent Swarm Syntax: An Approach to Live Coding with AI

Sven Hollowell, Pete Bennett, and Paul Marshall

Proceedings of the International Conference on New Interfaces for Musical Expression

Abstract

Collaborative live coding treats the shared text buffer as a stage where the act of typing forms part of the performance. Standard AI assistants, however, prioritise efficiency and opacity, often inserting code instantaneously and reducing the generative process to an invisible operation. This conflicts with live coding’s emphasis on visibility and audience legibility. We present a system built on top of Strudel, an interactive web-based live-coding environment, that re-frames Large Language Models (LLMs) as visible co-performers. Agents are spawned through inline comments (e.g., /// chaotic bass agent) and edit code through distinct cursors, generating text character- by-character alongside the human performer. A Conflict-Free Replicated Data Type (CRDT) editing model allows concurrent human and agent edits while maintaining a consistent shared document state. The system was evaluated through a collaborative autoethnographic study. The authors engaged in iterative performance sessions to identify emerging interaction patterns. Observations suggest that visible machine participation shifts the performer from direct creation toward curation, while preserving the performative “liveness” of live coding.

Citation

Sven Hollowell, Pete Bennett, and Paul Marshall. 2026. Multi-Agent Swarm Syntax: An Approach to Live Coding with AI . Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.20784519 [PDF]

BibTeX Entry

@inproceedings{nime2026_171,
 abstract = {Collaborative live coding treats the shared text buffer as a stage where the act of typing forms part of the performance. Standard AI assistants, however, prioritise efficiency and opacity, often inserting code instantaneously and reducing the generative process to an invisible operation. This conflicts with live coding’s emphasis on visibility and audience legibility. We present a system built on top of Strudel, an interactive web-based live-coding environment, that re-frames Large Language Models (LLMs) as visible co-performers. Agents are spawned through inline comments (e.g., /// chaotic bass agent) and edit code through distinct cursors, generating text character- by-character alongside the human performer. A Conflict-Free Replicated Data Type (CRDT) editing model allows concurrent human and agent edits while maintaining a consistent shared document state. The system was evaluated through a collaborative autoethnographic study. The authors engaged in iterative performance sessions to identify emerging interaction patterns. Observations suggest that visible machine participation shifts the performer from direct creation toward curation, while preserving the performative “liveness” of live coding.},
 address = {London, United Kingdom},
 articleno = {171},
 author = {Sven Hollowell and Pete Bennett and Paul Marshall},
 booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression},
 doi = {10.5281/zenodo.20784519},
 editor = {Benedict Gaster and João Tragtenberg and Anna Xambó and Tom Mitchell},
 issn = {2220-4806},
 month = {June},
 note = {},
 numpages = {5},
 pages = {1355--1359},
 title = {Multi-Agent Swarm Syntax: An Approach to Live Coding with AI },
 track = {paper},
 url = {http://nime.org/proceedings/2026/nime2026_171.pdf},
 year = {2026}
}