Back to feed
AR
arXiv CS.AI
6/29/2026
When Does Personality Composition Matter for Multi-Agent LLM Teams?

When Does Personality Composition Matter for Multi-Agent LLM Teams?

Short summary

Researchers test how personality prompting affects multi-agent LLM team performance across coding, collaboration, and bargaining tasks. Personality composition impacts vary by task type—minimal effect in coding but substantial performance degradation in collaborative and competitive scenarios. Key insight for multi-agent system architecture decisions.

  • •Personality composition effects on multi-agent performance depend critically on task structure
  • •Low agreeableness shifts communication style in coding with negligible performance impact
  • •Same personality manipulation substantially degrades performance in collaboration and bargaining

Generated with AI, which can make mistakes.

#research-breakthrough#ai-agents
Read full article at arXiv CS.AI

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

How Personas Can Influence Agents to Play Split or Steal
arXiv cs.CL
The original title is "Some Large Language Models Exhibit Consistent Risk Attitudes"
arXiv CS.AI
What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors
arXiv cs.CL
Prompt Robustness Is Task-Dependent: Comparing Objective and Belief-Style Questions in LLM Evaluation
arXiv cs.CL