Ellen Wenting Zou | Search arXiv

arXiv2026

Teachers' perspective on AI-based Multi-Agent Simulation Design to Combat School Bullying

Bullying in schools profoundly affects the mental and physical health of teenagers. Although existing in-person and digital interventions provide some benefits, they often fall short in addressing the complex social dynamics of bullying. In this study, we collaborated with K-12 teachers to co-design a multi-agent anti-bullying system powered by large language models (LLMs). This system simulates authentic scenarios, enabling students to develop anti-bully skills. The research identifies key design parameters for an LLM-driven multi-agent simulation system, offering valuable insights for creating more effective and scalable anti-bullying tools that could significantly reduce bullying in schools} \keywords{anti-bullying interventions, multi-agent system, generative AI, co-design, bystander presence

cs.HC↗

arXiv2026

On Emotion-Sensitive Decision Making of Small Language Model Agents

Small language models (SLM) are increasingly used as interactive decision-making agents, yet most decision-oriented evaluations ignore emotion as a causal factor influencing behavior. We study emotion-sensitive decision making by combining representation-level emotion induction with a structured game-theoretic evaluation. Emotional states are induced using activation steering derived from crowd-validated, real-world emotion-eliciting texts, enabling controlled and transferable interventions beyond prompt-based methods. We introduce a benchmark built around canonical decision templates that span cooperative and competitive incentives under both complete and incomplete information. These templates are instantiated using strategic scenarios from \textsc{Diplomacy}, \textsc{StarCraft II}, and diverse real-world personas. Experiments across multiple model families in various architecture and modalities, show that emotional perturbations systematically affect strategic choices, but the resulting behaviors are often unstable and not fully aligned with human expectations. Finally, we outline an approach to improve robustness to emotion-driven perturbations.

cs.AI↗