Get Started
Home
Topics
Search
Library
Research questionHow does LLM-agent proportion affect consensus and the legitimacy of resulting norms in mixed human–AI groups?As LLM agents participate in collective communication, changing their prevalence may alter not only whether groups converge but also what their shared conventions mean. Human and agent participants may differ in how they adopt, stabilize, and interpret emerging expressions.
AI
AI Agents
Multi-agent Systems
Natural Language Processing
Latest papersRecent research connected to this question, newest first.AI agents reshape consensus formation in human groupsThe evidence concerns mixed human–LLM groups playing a collaborative description game through repeated rounds of random pairwise communication. The study varies the proportion of LLM agents and reports low-, intermediate-, and high-agent regimes, including differences between human-led and agent-led consensus in convergence, semantic grounding, communicative form, and perceived legitimacy.research paper · Sep 2, 2026
Related questions
How does moral-dilemma context shape human and LLM judgments of autonomous agents’ moral agency?How can LLM agents participate in double auctions while preserving equilibrium convergence and efficient resource allocation?How can LLM orchestrators preserve continuous state when collaborating with non-language agents?How can we tell whether agreement among LLM judges reflects human alignment or shared blind spots?