Is There Any Social Principle for LLM-Based Agents?

TL;DR

This paper advocates for developing social science principles tailored to LLM-based agents, emphasizing their unique social interactions beyond traditional human-centered alignment.

Contribution

It introduces the idea of establishing dedicated social science frameworks specifically for LLM-based agents, moving beyond existing alignment approaches.

Findings

Highlights the importance of social principles for LLM agents

Proposes a new direction for agent-oriented social science

Encourages tailored social frameworks for AI agents

Abstract

Focus on Large Language Model based agents should involve more than "human-centered" alignment or application. We argue that more attention should be paid to the agent itself and discuss the potential of establishing tailored social sciences for agents.