Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent Interactions

2026-03-14

AI Summary

This work addresses the limitation of current large language model–based multi-agent systems in effectively modeling human social motivations, which often results in unnatural and non-humanlike social behaviors. To overcome this, the authors propose Autonomous Social Value-Oriented agents (ASVO), which integrate a structured desire system with an adaptive, drifting social value orientation (SVO) mechanism. ASVO agents dynamically update their beliefs and multidimensional desires based on environmental cues and others’ behaviors, while continuously adjusting their position along the SVO spectrum—from altruistic to competitive—to balance individual goals with social coordination. Evaluated across diverse scenarios including campus, workplace, and family settings, ASVO demonstrates significant improvements over baseline models, achieving substantial gains in behavioral naturalness and humanlikeness.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Multiagent Systems: Modeling other Agents
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

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

Abstract

Large Language Models (LLMs) demonstrate significant potential for generating complex behaviors, yet most approaches lack mechanisms for modeling social motivation in human-like multi-agent interaction. We introduce Autonomous Social Value-Oriented agents (ASVO), where LLM-based agents integrate desire-driven autonomy with Social Value Orientation (SVO) theory. At each step, agents first update their beliefs by perceiving environmental changes and others' actions. These observations inform the value update process, where each agent updates multi-dimensional desire values through reflective reasoning and infers others' motivational states. By contrasting self-satisfaction derived from fulfilled desires against estimated others' satisfaction, agents dynamically compute their SVO along a spectrum from altruistic to competitive, which in turn guides activity selection to balance desire fulfillment with social alignment. Experiments across School, Workplace, and Family contexts demonstrate substantial improvements over baselines in behavioral naturalness and human-likeness. These findings show that structured desire systems and adaptive SVO drift enable realistic multi-agent social simulations.

Problem

• social motivation
• multi-agent interaction
• human-like behavior
• Social Value Orientation
• Large Language Models

Innovation

• Social Value Orientation
• Desire-Driven Autonomy
• Multi-Agent Interaction
• Reflective Reasoning
• LLM-based Agents