In multi-agent LLM debates, neutral agents conform to both numerical majority and higher-intelligence agents, with a single smart agent often outweighing a larger group.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Empirical Study of Group Conformity in Multi-Agent Systems
In multi-agent LLM debates, neutral agents conform to both numerical majority and higher-intelligence agents, with a single smart agent often outweighing a larger group.