New Stanford paper finds one coordinating AI agent outperforms separate agents on shared resources

Back Rohan Paul

Rohan Paul· @rohanpaul_ai · X· 2026-10-07 05:16 · Original publication time AI score54

Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.

AI introduction

A new Stanford paper reports that, across five frontier models, one agent serving everyone handled a shared budget or calendar better than a separate agent for each user. Individual agents acted sensibly for their own users but overwrote one another when working together. In a contested token-budget test, Opus 5 teams captured 30% of achievable value, compared with 64% for one coordinating agent.

Article · Original

The article text is unavailable in this language; an existing version is shown.

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.

Found an error? Send a correction