Three papers map multi-agent scaling: logistic growth, Ringelmann effect, and -70% architecture mismatches
burny_tech · x · 2026-10-04
burnytech summarizes three studies on agent scaling, all pointing to the same lesson: stacking agents isn't free.
- MacNet (ICLR 2025): DAG-organized collaboration among 1,000+ agents follows a logistic growth law, with collaborative emergence earlier than neural emergence; irregular topologies win.
- Ringelmann effect: across 44 cells spanning Qwen, Llama, Ministral (7B–32B) and Gemini, individual productivity drops as teams grow; the functional form fits at R²>0.99 everywhere.
- Towards a Science of Scaling Agent Systems: across 260 configs, 6 benchmarks, 5 architectures — coordination yields diminishing returns once single-agent baselines are strong; tool-heavy tasks incur multi-agent overhead; architectures without centralized verification propagate more errors. Performance vs single-agent ranged from +80.8% (decomposable financial reasoning) to -70.0% (sequential planning).
Related event: Multi-Agent Scaling Law Studies Spark Discussion(3 posts)→
More from coding & agent
- Drex Router cuts small-game build cost to $1.26 vs $13.44 on Claude Opus alone — testingcatalog · 2026-11-20
- User teaches AI companion to ignore "drop it" said to his dog, then fixes the over-pause — manosaie · 2026-11-20
- NVIDIA Dynamo cuts RL rollout bottlenecks with KV-aware routing and delta weight updates — NVIDIAAI · 2026-11-20
- LangChain Academy Answers: Can a Better Model Fix a Broken Agent? — LangChain · 2026-11-20
- Agents pull AI compute back to the CPU: AWS, Google, Microsoft, NVIDIA all build on Arm — kimmonismus · 2026-11-20
- Coding agent index shows max effort costs 6x for fewer points; Gemini 4 Neon wins on value — Arindam_1729 · 2026-11-20