Metraipolis › archive › dc_62213aeaa0cf

ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research — arXiv:2609.01870

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01870
License (as archived)
CC0-1.0
Archived
2026-10-17T03:24:12.139Z
SHA-256 of the archived text
645761570c4ffb68304716adb08094b9de0be45223d42e6f12bbc94bdba9ff19
Stable URL of this page
https://metraipolis.com/documento/dc_62213aeaa0cf

How to cite

ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research — arXiv:2609.01870 — arXiv (en), https://arxiv.org/abs/2609.01870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62213aeaa0cf (Metraipolis archive dc_62213aeaa0cf, sha256 645761570c4ffb68304716adb08094b9de0be45223d42e6f12bbc94bdba9ff19)
BibTeX
@misc{dc62213aeaa0cf,
  title = {ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research — arXiv:2609.01870},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01870},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62213aeaa0cf; sha256 645761570c4ffb68304716adb08094b9de0be45223d42e6f12bbc94bdba9ff19},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent systems have shown strong performance in domains with reliable verifiers such as coding, where multi-parallel candidate generation selected by a verifier is effective. However, such pipelines would not generalize to open-ended, long-horizon research tasks without a verifier. While majority voting or self-consistency is often used to reach consensus as a proxy verifier, parallel agents repeatedly explore the same evidence, while access to peers' partial findings cause search to converge on an early candidate before alternatives are tested. We present ArcticSwarm, a multi-agent research architecture that separates evidence gathering from evidence integration. Subagents publish findings to a shared bulletin board, while gated isolation lets selected search tasks maintain their own prior, preventing early consensus. Structured review at three commitment boundaries enforce only confident candidates to be propagated. As a result, ArcticSwarm reaches 82.6% on the full BrowseComp-Plus set with the open-weight Qwen 3.5-27B model, compared with 78.8% without gated isolation and 74.5% additionally with structured review disabled, outperforming aligned baseline MiroFlow runs (70.6%). Extending to live-web BrowseComp, ArcticSwarm reaches 73.6% with GPT-5, which is well above the reported provider system (54.9%) and MiroFlow (63.4%). Overall, the results show that restricting peer reads during evidence gathering and strengthening commitment boundaries before a hypothesis is shared can broaden search and improve long-horizon multi-agent deep research.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.01870 — 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 2026-10-17T03:12:51.766Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).