Article · Original
The article text is unavailable in this language; an existing version is shown.
– https://t.co/awL07ExeOk
Title: "Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams"
Stanford study finds that separate user agents struggle to coordinate shared resourcesMachine translation
Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.
A Stanford study compared tasks involving shared budgets and calendars across five frontier models. Teams with one agent per user performed worse overall than a single agent coordinating for everyone. On a contested token budget, Opus 5 teams captured 30% of the achievable value, versus 64% for one coordinating agent.
New Stanford paper finds that when each person's agent acts alone on a shared resource, the group does worse than 1 agent serving everyone.
A shared budget or calendar is handled better by 1 agent serving everyone than by 1 agent per user, across 5 frontier models.
Each agent does a sensible job for its own user.
Together they overwrite each other, stall as the team grows, and with no channel they collapsed outright in 2 environments.
On a contested token budget, Opus 5 teams captured 30% of the achievable value against 64% for 1 coordinating agent.
Agents invented facts about other users in more than half of Claude team episodes in the group-ordering environment.
Prefer 1 agent holding everyone's constraints, and if you run 1 per user, make reading peers a condition of committing.
View replied-to post on X