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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Jingzhe, Zhang, Ceyao, Yang, Yaodong, Wang, Yizhou, Zhu, Song-Chun, Zhong, Fangwei
Format:	Preprint
Published:	2026
Subjects:	Multiagent Systems
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866910052876550144
author	Lin, Jingzhe Zhang, Ceyao Yang, Yaodong Wang, Yizhou Zhu, Song-Chun Zhong, Fangwei
author_facet	Lin, Jingzhe Zhang, Ceyao Yang, Yaodong Wang, Yizhou Zhu, Song-Chun Zhong, Fangwei
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2603_13890
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent Interactions Lin, Jingzhe Zhang, Ceyao Yang, Yaodong Wang, Yizhou Zhu, Song-Chun Zhong, Fangwei Multiagent Systems 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.
title	Beyond Self-Interest: Modeling Social-Oriented Motivation for Human-like Multi-Agent Interactions
topic	Multiagent Systems
url	https://arxiv.org/abs/2603.13890