A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios

Authors: Xiachong Feng, Longxu Dou, Minzhi Li, Qinghao Wang, Yu Guo, Haochuan Wang, Chang Ma, Lingpeng Kong

TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios. While numerous studies have explored these agents in such settings, there is a lack of a comprehensive survey summarizing the current progress. To address this gap, we systematically review existing research on LLM-based social agents within game-theoretic scenarios.
Researcher Affiliation Academia µThe University of Hong Kong s Independent Researcher αNational University of Singapore γInstitute for Infocomm Research (I2R), A*STAR δPeking University βHarbin Institute of Technology EMAIL,EMAIL
Pseudocode No The paper does not contain any sections explicitly labeled "Pseudocode" or "Algorithm", nor does it present any structured code-like blocks describing a method or procedure.
Open Source Code No The paper is a survey and does not describe new methodology that would typically be accompanied by source code. It discusses open-source code in the context of other research it reviews, but does not provide its own.
Open Datasets No The paper is a survey and does not introduce new datasets. It mentions datasets and benchmarks from other research papers it reviews, but does not provide access information for a dataset created or utilized by the authors of this survey for their own methodology.
Dataset Splits No The paper is a survey and does not conduct its own experiments; therefore, it does not provide dataset splits for reproduction.
Hardware Specification No The paper is a survey and does not describe any specific hardware used for running its own experiments or analyses.
Software Dependencies No The paper is a survey and does not describe any specific software dependencies or versions used for running its own methodology or analyses.
Experiment Setup No The paper is a survey and does not present any original experimental work; therefore, it does not include details about an experimental setup, hyperparameters, or training settings.