More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs
Summary
This study disentangles three factors often confused in multi-agent evaluations, clarifying whether gains come from coordination between agents, ensembling results, or simply more test-time compute.
Why this matters
Covers model and LLM · Relevant to this topic
Source: arXiv cs.AI · arxiv.org