Metraipolis › archive › dc_483ff24993dc

Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense — arXiv:2610.41044

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41044
License (as archived)
CC0-1.0
Archived
2026-11-03T07:31:14.026Z
SHA-256 of the archived text
015f62dd039e2894a66a5debc3754bbcf544e0ec1fa3b8dfb02c93e462fa22c1
Stable URL of this page
https://metraipolis.com/documento/dc_483ff24993dc

How to cite

Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense — arXiv:2610.41044 — arXiv (en), https://arxiv.org/abs/2610.41044 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_483ff24993dc (Metraipolis archive dc_483ff24993dc, sha256 015f62dd039e2894a66a5debc3754bbcf544e0ec1fa3b8dfb02c93e462fa22c1)
BibTeX
@misc{dc483ff24993dc,
  title = {Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense — arXiv:2610.41044},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41044},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_483ff24993dc; sha256 015f62dd039e2894a66a5debc3754bbcf544e0ec1fa3b8dfb02c93e462fa22c1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41044. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The use of large language models (LLMs) to coordinate multi-agent teams raises a fundamental architectural question: whether task allocation should be centralized in a single LLM controller or distributed across autonomous LLM agents, particularly when communication is unreliable. In a deliberately simplified perimeter-defense simulation against LLM-controlled intruders, we compared a central commander, an auction-based consensus team and independent agents under five network conditions. Breach rates were 15% for the consensus team, 32% for the commander and 29% for independent agents, and of the different network conditions, only limited radio range changed a team's breach rate, raising the commander's. In consensus team, giving a low-cost LLM more authority over the bid computation raised breaches by 38 percentage points. With birds and civilian drones in airspace, we added a photograph for each to the input text state. Only the near-frontier model treated them apart from intruders. Intruders disguised as existing taxidermy bird drones were mistook as birds by both low-cost and near-frontier LLMs, going unpursued in 59-61% of near-frontier decisions (1-16% before). However, a one-sentence forewarning in the prompt lowered it to 0-25%. We find that LLM team with a dedicated external conflict resolution protocol results in fewest breaches. Code: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.41044 — 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 2026-11-03T07:29:33.589Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).