AI RESEARCH
When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines
arXiv CS.AI
•
ArXi:2603.20324v1 Announce Type: cross Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality: heterogeneous Mixture-of-Agents teams outperform single models, yet homogeneous Self-MoA teams consistently win under synthesis-based aggregation. We propose a resolution by identifying the selection bottleneck -- a crossover threshold in aggregation quality that determines whether diversity helps or hurts.