Metraipolis › archive › dc_dd8925dd830f
s$^3$: Simple Scaling of Swarms via Cooperative Multi-agent RL — arXiv:2611.08615
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08615
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:33:29.967Z
- SHA-256 of the archived text
4adc1a2ee7e1e6d8a4183df6518cbbac56f40b801d691b2d8af3b58f4875638c- Stable URL of this page
https://metraipolis.com/documento/dc_dd8925dd830f
How to cite
s$^3$: Simple Scaling of Swarms via Cooperative Multi-agent RL — arXiv:2611.08615 — arXiv (en), https://arxiv.org/abs/2611.08615 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd8925dd830f (Metraipolis archive dc_dd8925dd830f, sha256 4adc1a2ee7e1e6d8a4183df6518cbbac56f40b801d691b2d8af3b58f4875638c)
BibTeX
@misc{dcdd8925dd830f,
title = {s$^3$: Simple Scaling of Swarms via Cooperative Multi-agent RL — arXiv:2611.08615},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08615},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd8925dd830f; sha256 4adc1a2ee7e1e6d8a4183df6518cbbac56f40b801d691b2d8af3b58f4875638c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08615. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Groups can achieve more than individuals in the same amount of time, but only if their members coordinate: they must decide who works on what and what to share. However, this organization in multi-agent systems today usually comes from arbitrary, static harnesses designed a priori without adapting to agent behaviors or task specifications. We ask whether agents can instead learn to organize themselves. We introduce s$^3$, the first multi-agent reinforcement learning method in which agents decide for themselves how long to work alone and when to share findings or read teammates' messages, with no predefined organization or roles. Our s$^3$ agents learn to take different approaches, read each other's work, exhibit emergent roles that complement each other in the swarm, and generalize to bigger teams. We study both coordination, where agents must combine private information, and parallel exploration, where sharing discoveries can make search more efficient. With matched training and inference budgets, s$^3$, swarms evaluated with twice as many agents as in training solve over 25$\times$ more coordination problems than the strongest baseline, and in exploration, communicating agents reduce repeated work by nearly 50% and outperform best-of-N by up to 9.4 percentage points. Rather than being designed in advance, s$^3$ enables organization to emerge from a shared goal. This opens the door to capable systems built from many models that learn to work together. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.08615 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:30:32.041Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).