Metraipolis › archive › dc_a8a681889176
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization — arXiv:2611.08483
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08483
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:42:03.750Z
- SHA-256 of the archived text
db65675322db02d673c181348c0904fd9c58b4247841960e05bd7ca28073625e- Stable URL of this page
https://metraipolis.com/documento/dc_a8a681889176
How to cite
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization — arXiv:2611.08483 — arXiv (en), https://arxiv.org/abs/2611.08483 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a8a681889176 (Metraipolis archive dc_a8a681889176, sha256 db65675322db02d673c181348c0904fd9c58b4247841960e05bd7ca28073625e)
BibTeX
@misc{dca8a681889176,
title = {SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization — arXiv:2611.08483},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08483},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a8a681889176; sha256 db65675322db02d673c181348c0904fd9c58b4247841960e05bd7ca28073625e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08483. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches. Each swarm studies the problem from a different angle. A novelty filter keeps the most distinct agent ideas by directly measuring the distances between the agents' hidden state vectors. Crossover of ideas happens naturally in latent space, as a summarizer agent receives the combined KV caches of all swarm members. On 21 problems in mathematical discovery and scientific computing, SwarmEvolve gets the highest average score and needs a median of only 3 to 8 minutes to reach the best scores that other state-of-the-art frameworks reach in 60 minutes. On several problems, SwarmEvolve with Qwen3 8B improves on the solutions that AlphaEvolve first found with frontier LLMs. Our work shows that agent swarms that communicate in latent space offer a fast, low-cost approach to program search for scientific problems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2611.08483 — 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 2026-11-06T14:18:42.660Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).