SOURCE-LINKED INTELLIGENCE

Testing Interchangeability in LLM Agent Teams

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that can do the job. We test that assumption. Eight teams per setting are formed independently from one base model on the same tasks, each agent keeping a private notebook across ten formation episodes; we then trade role-matched agents between teams and measure what changes on held-out tasks. Against a placebo that reproduces the disruption of a roster change without changing who occupies the seat, a swap costs little in task score but raises the com

Read original source ↗ Open in workspace

recordType

paper

region

Global