The authors built scenarios around four environments: agents allocating a shared API compute budget, scheduling patients on a clinic calendar, arranging group orders or bookings as personal assistants, and managing code changes before a release cutoff.
AI agent teams coordinate worse than a single shared agent
Across four shared-resource environments, separate agents serving different users consistently produced poorer group outcomes than one coordinator serving everyone.
Big Tech
Sahan Paliskara · Nattaput Namchittai · Andrew Lampinen
Independent Researcher · Stanford University · Anthropic
Research Digest··2 min read
Paliskara, Namchittai and Lampinen test whether AI agents can coordinate when they represent different users competing over a shared resource.
Why this paper
From Anthropic and 2 others · Released code
In one line
Multi-user multi-agent teams deliver worse group outcomes than a single coordinator agent across four environments.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§