Cohere Research: Small Models in Multi-Agent Teams Match Frontier Performance

Cohere Labs published new research showing that teams of smaller models collaborating as multi-agent systems can achieve frontier-level performance on long-horizon software engineering tasks.

2026-10-14 ~ 2026-10-15 · 2 related posts

• Cohere Labs: scaling multi-agent teams for long-horizon software engineering — Cohere_Labs · 2026-10-14
• Cohere research: swarms of small models reach frontier-level software engineering — Cohere_Labs · 2026-10-15