How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study

arXiv:2604.06562v1 Announce Type: new Abstract: Small language models (SLM) are increasingly used as interactive decision-making agents, yet most decision-oriented evaluations

arXiv:2603.22295v1 Announce Type: cross Abstract: Large language models appear to develop internal representations of emotion -- "emotion circuits," "emotion neurons," and

arXiv:2603.22306v1 Announce Type: new Abstract: Affective judgment in real interaction is rarely a purely local prediction problem. Emotional meaning often depends on prior

arXiv:2603.23406v1 Announce Type: new Abstract: While large language models simulate social behaviors, their capacity for stable stance formation and identity negotiation during

arXiv:2605.04454v1 Announce Type: new Abstract: Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under

arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to

arXiv:2605.20200v1 Announce Type: cross Abstract: This article presents a multimodal emotion recognition module integrated into a proactive Socially Interactive Agent (SIA)

arXiv:2603.18743v1 Announce Type: new Abstract: We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing