Tag
Introduces TRIBE, a domain-independent pipeline that uses topic modeling and clustering on team communication to predict performance early and analyze how AI agents alter team behavioral dynamics.
This paper systematically examines how manipulating personality traits in multi-agent LLM teams affects performance across coding, research collaboration, and bargaining tasks, finding that effects depend critically on task structure.
The article argues that increasing the amount of AI-generated code does not necessarily improve team speed and may even reduce efficiency.