Swarm

MAServeBench held the generated work fixed and changed only the order in which agents were allowed to run. Median deadline attainment went from 100% to 4%. October's measurements put the cost of a swarm at the deadline, and the token meter is the smaller bill.

The framework debate consolidated into a spectrum. The next argument is over orchestration topology: every multi-agent design reduces to who holds state and control, and a February 2026 research cluster is formalizing that choice as an optimization problem rather than a brand pick.