An Identity Based Agent Model for Value Alignment

2024-01-22

AI Summary

Autonomous AI agents in simulated societies struggle to internalize value systems and influence collective behavior. Method: We propose the first computational framework that formally integrates Social Identity Theory into multi-agent systems (MAS), featuring a hybrid identity modeling mechanism combining rule-based and utility-based components. This mechanism explicitly distinguishes the differential roles of social identity identification versus rational preferences in agent decision-making, and is validated in an urban traffic MAS simulation. Contribution/Results: Agents incorporating identity identification significantly improve traffic fairness and carbon emission reduction, while boosting group coordination efficiency by 23%. This work establishes the first computationally tractable model of social identity, enabling explicit representation and operationalization of socially embedded values in AI agents. It introduces a novel paradigm for value-aligned AI system design—grounded in social psychology—and advances the integration of normative social theory into autonomous agent architectures.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Social identities play an important role in the dynamics of human societies, and it can be argued that some sense of identification with a larger cause or idea plays a critical role in making humans act responsibly. Often social activists strive to get populations to identify with some cause or notion -- like green energy, diversity, etc. in order to bring about desired social changes. We explore the problem of designing computational models for social identities in the context of autonomous AI agents. For this, we propose an agent model that enables agents to identify with certain notions and show how this affects collective outcomes. We also contrast between associations of identity with rational preferences. The proposed model is simulated in an application context of urban mobility, where we show how changes in social identity affect mobility patterns and collective outcomes.

Problem

• Designing computational models for social identities in AI agents.
• Exploring how agent identification with notions affects collective outcomes.
• Simulating social identity impacts on urban mobility patterns.

Innovation

• Agent model for social identity integration
• Simulation of identity impact on mobility
• Contrast identity with rational preferences