RESEARCHInvestigateNEXT 12 MONTHS
More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs
arXiv cs.LG — Machine Learning
Factual evidence
What the source reports
A paper synthesising 516 multi-agent LLM setups shows benchmark gains often stem from extra sampling or compute rather than coordination.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.LG — Machine Learning · RESEARCH
- Published by source
- 16 November 2026
- Collected by OneBench
- 17 Nov 2026, 02:01 UK
Stored source excerpt
arXiv:2611.17610v1 Announce Type: cross Abstract: Evaluations of multi-agent language models often compare communicating architectures against a single greedy pass. This practice confounds coordination with sample…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.