2 papers
cs.MA2026
"Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse
Shiyang Lai, Arna Woemmel, Hongkai Mao +3
Semantic collapse, the progressive narrowing of what AI systems generate, has been studied mainly in closed settings, and remedies have targeted models and data. We study it in MOL…
cs.MA2026
The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
Summer Eunhyung Ann, Haokun Liu, Chenhao Tan
Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture-of-agents synthesis (Wang et a…