Sentipolis: Emotion-Aware Agents for Social Simulations

2026-01-25

AI Summary

This work addresses the limitation of current large language model (LLM) agents in social simulations, which often treat emotions as transient signals, leading to affective amnesia and behavioral inconsistency. To overcome this, we propose the first agent framework that supports long-term emotional memory and dynamic evolution, leveraging a continuous Pleasure-Arousal-Dominance (PAD) emotion representation, dual-timescale emotional dynamics, and an emotion-driven memory integration mechanism to enable sustained modeling of affective states. Experimental results demonstrate that our approach significantly enhances emotional grounding, communication quality, and affective continuity over thousands of interactions. At the network level, stable, reciprocal, and moderately clustered social structures emerge, facilitating the study of cumulative social dynamics such as alliance formation. The findings also reveal the advantage of high-capacity models in emotional plausibility and their inherent trade-offs with adherence to social norms.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Emotional Intelligence

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

LLM agents are increasingly used for social simulation, yet emotion is often treated as a transient cue, causing emotional amnesia and weak long-horizon continuity. We present Sentipolis, a framework for emotionally stateful agents that integrates continuous Pleasure-Arousal-Dominance (PAD) representation, dual-speed emotion dynamics, and emotion--memory coupling. Across thousands of interactions over multiple base models and evaluators, Sentipolis improves emotionally grounded behavior, boosting communication, and emotional continuity. Gains are model-dependent: believability increases for higher-capacity models but can drop for smaller ones, and emotion-awareness can mildly reduce adherence to social norms, reflecting a human-like tension between emotion-driven behavior and rule compliance in social simulation. Network-level diagnostics show reciprocal, moderately clustered, and temporally stable relationship structures, supporting the study of cumulative social dynamics such as alliance formation and gradual relationship change.

Problem

• emotion-aware agents
• social simulation
• emotional continuity
• emotional amnesia
• LLM agents

Innovation

• emotion-aware agents
• PAD representation
• emotion-memory coupling
• social simulation
• dual-speed emotion dynamics