A new paper explores how large language model (LLM) agents can exhibit emergent emotional contagion within simulated crowds. The study, which uses a multi-agent crowd simulation, found that agents perceive, appraise, and express emotions based on their prompted personality, memory, and context. The research demonstrates that emotional states can spread through these agents, with the dynamics influenced by factors like spatial layout, temporal progression, and the agents' personality profiles. The paper also notes that the observed emotional contagion is dependent on the specific LLM backend used for appraisal. AI
IMPACT This research could inform the development of more sophisticated and nuanced AI agents capable of complex social interactions.
RANK_REASON The cluster contains an academic paper detailing a novel research finding.
Read on arXiv cs.MA (Multiagent) →
- arXiv
- crowd simulation
- emotional contagion
- Funda Durupinar Babur
- Hugging Face
- LLM agents
- Russell's Circumplex Model of Affect
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
