research
Swapping One Agent Raised Coordination Costs Up to 63 Percent
Role-matched replacements preserved much of the task score but made independently formed teams communicate far more for each unit of progress.
Summary
Role-matched replacements preserved much of the task score but made independently formed teams communicate far more for each unit of progress.
The study formed eight teams per setting from the same base model, let each agent keep a private notebook over ten formation episodes and then traded role-matched agents between teams. Compared with a placebo roster disruption, swaps changed task score little but increased communication per unit of progress by 16 to 63 percent. In Hanabi, a swapped agent could cost more than an inexperienced one; in Collab-Overcooked, replacing the agenda setter shifted much of the extra communication onto the agent that stayed. The penalty tracked how far team conventions had drifted, suggesting role capability and coordination fit are different forms of interchangeability.
Why it matters
Role-matched replacements preserved much of the task score but made independently formed teams communicate far more for each unit of progress.
Limits and context
No additional limitation was separately recorded.
Key claims
Role-matched replacements preserved much of the task score but made independently formed teams communicate far more for each unit of progress.
Evidence: source-2026-09-08-015
Sources
- arXiv preprint 2609.05279arXiv · primary research
Corrections
No corrections have been recorded for this story.