More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs

arXiv:2611.17610 · cs.AI, cs.CL, cs.LG, cs.MA · Submitted 2026-11-13 · Read on arXiv

cs.AI, cs.CL, cs.LG, cs.MA

Submitted: 2026-11-13

Updated: 2026-11-13

Terminology

Related papers