LLM-enabled Social Agents

TL;DR

This paper argues that grounding LLM-enabled social agents in role-based personas is essential for meaningful social behavior, outlining research directions for their development and evaluation.

Contribution

It introduces the concept of role-based persona grounding as a foundation for social agents using LLMs, addressing current limitations in social behavior.

Findings

Persona-based role definitions are crucial for social behavior in LLM agents.

Current systems lack grounding in roles, norms, and context, limiting social interaction.

Research directions include representation, hybrid control, and evaluation methods.

Abstract

Large Language Models (LLMs) have transformed agent-agent and human-agent interaction by enabling software, physical, and simulation agents to communicate and deliberate through natural language. Yet fluent language use does not by itself yield socially intelligible behaviour. Most current systems remain weakly grounded in roles, norms, intentions, and contextual constraints, limiting their capacity for meaningful participation in social environments. This paper develops a conceptual baseline for LLM-enabled social agents by arguing that they should be grounded in role definitions operationalized through persona descriptions. On this basis, we outline research directions for representation, hybrid control, and evaluation. The paper concludes that persona-based role definitions are a necessary foundation for turning language competence into social behaviour.