The Bystander Effect in Multi-Agent Reasoning: Adding Agents Can Make LLMs Dumber

arXiv·high signal

Across 22,500 deterministic trajectories on GAIA, SWE-bench, and Multi-Challenge with 3 SOTA models, researchers demonstrate that multi-agent collaboration triggers an algorithmic 'Bystander Effect' — cognitive loafing where individual agents produce shallower reasoning traces when they believe other agents are present. This directly challenges the assumption that more agents equals better performance and has immediate implications for multi-agent system design.