Tech · Apple Machine Learning
Multi-Agent Teams Hold Experts Back
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
Multi-Agent Teams Hold Experts Back.
Key facts
- Across human-inspired and frontier ML benchmarks, they find that, unlike human teams, LLM teams consistently fail to match their expert agent’s performance, even when explicitly told who the expert
- Authors Aneesh Pappu†, Batu El†, Hancheng Cao‡, Carmelo di Nolfo, Yanchao Sun, Meng Cao, James Zou†
- Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows
- Drawing on organizational psychology, they study whether self-organizing LLM teams achieve strong synergy, where team performance matches or exceeds the best individual member
Summary
Authors Aneesh Pappu†, Batu El†, Hancheng Cao‡, Carmelo di Nolfo, Yanchao Sun, Meng Cao, James Zou†. Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. Drawing on organizational psychology, they study whether self-organizing LLM teams achieve strong synergy, where team performance matches or exceeds the best individual member. Across human-inspired and frontier ML benchmarks, they find that, unlike human teams, LLM teams consistently fail to match their expert agent’s performance, even when explicitly told who the expert is, incurring performance losses of up to 41.1% on ML benchmarks.