AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios

Large language models (LLMs) are increasingly leveraged to empower autonomous agents to simulate human beings in various fields of behavioral research. However, evaluating their capacity to navigate complex social interactions remains a challenge. Previous studies face limitations due to insufficien...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Mou, Xinyi, Liang, Jingcong, Lin, Jiayu, Zhang, Xinnong, Liu, Xiawei, Yang, Shiyue, Ye, Rong, Chen, Lei, Kuang, Haoyu, Huang, Xuanjing, Wei, Zhongyu
Format: Article
Language:English
Subjects:
Autonomous navigation
Benchmarks
Complexity
Large language models
Reasoning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Large language models (LLMs) are increasingly leveraged to empower autonomous agents to simulate human beings in various fields of behavioral research. However, evaluating their capacity to navigate complex social interactions remains a challenge. Previous studies face limitations due to insufficient scenario diversity, complexity, and a single-perspective focus. To this end, we introduce AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios. Drawing on Dramaturgical Theory, AgentSense employs a bottom-up approach to create 1,225 diverse social scenarios constructed from extensive scripts. We evaluate LLM-driven agents through multi-turn interactions, emphasizing both goal completion and implicit reasoning. We analyze goals using ERG theory and conduct comprehensive experiments. Our findings highlight that LLMs struggle with goals in complex social scenarios, especially high-level growth needs, and even GPT-4o requires improvement in private information reasoning. Code and data are available at \url{https://github.com/ljcleo/agent_sense}.
ISSN:2331-8422