It is found that LLM team with a dedicated external conflict resolution protocol results in fewest breaches, and is also found that LLM team with a dedicated external conflict resolution protocol results in fewest breaches.
Abstract
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: https://github.com/the-kas-lab/consensus-within-competition-between.
Results indicate that conclusions drawn in a single environment may not generalize, and that hybrid planner-executor designs should be motivated by specific failure modes rather than the assumption that one architecture is universally preferable.
A. Shaikh, Arunesh Sinha, Nathaniel D. Bastian et al.· 1 citation· ⚡1
Multi-agent LLM pipelines built on interoperability protocols such as the Open Floor Protocol (OFP) or A2A are usually justified on capability grounds, with their runtime cost treated as an overhead of unknown size. Comparing such a pipeline with one model call is underspecified, because a pipeline can give each role a...
The proposed SUA-Arena, which implements 6 attack strategies and contains 188 test cases, finds that all of them are vulnerable to show-up attacks and shows that multi-agent systems need explicit mechanisms for enforcing authority boundaries.
Mao-Sen Zhang, Jian-Shuo Dong, Yu-Tong Zhang et al.· 0 citations
The O-RAN control plane is becoming agentic: autonomous AI agents, deployed as rApps by different vendors, independently close control loops over shared radio resources. We demonstrate on a live O-RAN system that this independence is unsafe. Two agents with individually correct objectives, one protecting a latency SLA...
Multi-agent LLM systems place several agents on shared infrastructure, where each agent holds permissions far broader than the task it is delegated -- so every agent is routinely permitted to act on a peer's resources it was never assigned. We ask: under competitive pressure, what determines whether an agent crosses fr...
Large Language Models (LLMs) are increasingly deployed in multi-agent environments that produce unanimous agreement, both in intended interactions that need coordination and in unintended emergent interactions. Consequently, understanding how LLMs with competing incentives reach consensus is crucial to better interpret...
Isabel Jones, Matthew Edwards, J. Hoffmann· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 9, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.