跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2610.41044 · v2

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

首次提交 2026-10-30 06:34
版本更新 2026-11-15 04:07
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

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. Burst message loss, falsified reports and limited radio range raised the commander's breach rate by 10 to 18 percentage points (pp), whereas the consensus team's changed by at most 5. In the consensus team, giving a low-cost LLM more authority over the bid computation raised its breach rate by 38 pp. With birds and civilian drones in airspace, we added an image 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 mistaken for birds by both low-cost and near-frontier LLMs, being dropped from pursuit 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 the LLM team with a dedicated external conflict-resolution protocol had the fewest breaches. The code is available at https://github.com/the-kas-lab/consensus-within-competition-between.

作者备注:97 pages (37 main text and references, 60 supplementary information), 7 main figures. Code: https://doi.org/10.5281/zenodo.24209157. Data: https://doi.org/10.5281/zenodo.24208099

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-15 04:07 · 最新观测版本

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

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. Burst message loss, falsified reports and limited radio range raised the commander's breach rate by 10 to 18 percentage points (pp), whereas the consensus team's changed by at most 5. In the consensus team, giving a low-cost LLM more authority over the bid computation raised its breach rate by 38 pp. With birds and civilian drones in airspace, we added an image 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 mistaken for birds by both low-cost and near-frontier LLMs, being dropped from pursuit 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 the LLM team with a dedicated external conflict-resolution protocol had the fewest breaches. The code is available at https://github.com/the-kas-lab/consensus-within-competition-between.

查看此版本解读 →查看此版本原文 ↗