LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans
Institute for Artificial Intelligence Research and Development of Serbia（塞尔维亚人工智能研究与开发研究所）；University of Belgrade, Institute for Philosophy and Social Theory, Digital Society Lab（贝尔格莱德大学，哲学与社会理论研究所，数字社会实验室）；Complexity Science Hub, Vienna, Austria（维也纳复杂科学中心）；Graz University of Technology, Graz, Austria（技术大学格拉茨，格拉茨，奥地利）；University of Novi Sad, Faculty of Philosophy, Novi Sad, Serbia（诺维萨德大学，哲学学院，诺维萨德，塞尔维亚）；University of Trier, Trier, Germany（特里尔大学，特里尔，德国）；Vrije University Amsterdam, Amsterdam, Netherlands（阿姆斯特丹自由大学，阿姆斯特丹，荷兰）
Ljubisa Bojic, Alexander Felfernig, Bojana Dinic, Velibor Ilic, Achim Rettinger, Vera Mevorah, Damian Trilling
Social media platforms mediate how billions form opinions and engage with public discourse. As autonomous AI agents increasingly participate in these spaces, understanding their behavioral fidelity becomes critical for platform governance and democratic resilience. Previous work demonstrates that LLM-powered agents can replicate aggregate survey responses, yet few studies test whether agents can predict specific individuals' reactions to specific content. This study benchmarks LLM-based agents' accuracy in predicting human social media reactions (like, dislike, comment, share, no reaction) across 120,000+ unique agent-persona combinations derived from 1,511 Serbian participants and 27 large language models. In Study 1, agents achieved 70.7% overall accuracy, with LLM choice producing a 13 percentage-point performance spread. Study 2 employed binary forced-choice (like/dislike) evaluation with chance-corrected metrics. Agents achieved Matthews Correlation Coefficient (MCC) of 0.29, indicating genuine predictive signal beyond chance. However, conventional text-based supervised classifiers using TF-IDF representations outperformed LLM agents (MCC of 0.36), suggesting predictive gains reflect semantic access rather than uniquely agentic reasoning. The genuine predictive validity of zero-shot persona-prompted agents warns against potential manipulation through easily deploying swarms of behaviorally distinct AI agents on social media, while simultaneously offering opportunities to use such agents in simulations for predicting polarization dynamics and informing AI policy. The advantage of using zero-shot agents is that they require no task-specific training, making their large-scale deployment easy across diverse contexts. Limitations include single-country sampling. Future research should explore multilingual testing and fine-tuning approaches.
From Profiling to Synthesis: Benchmarking Implicit Behavioral Alignment in Personalized LLM Agents
National University of Singapore（新加坡国立大学）；University of Toronto（多伦多大学）；University of Minnesota Twin Cities（明尼苏达大学双城分校）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；University of Oxford（牛津大学）
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
University of Science and Technology of China（中国科学技术大学）；City University of Hong Kong（香港城市大学）；Northeastern University（东北大学）；MemTensor (Shanghai) Technology Co., Ltd.（MemTensor（上海）科技有限公司）
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
Beijing Institute of Technology（北京理工大学）；Huawei Technologies Co., Ltd（华为技术有限公司）；Peking University（北京大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation（中国科学院自动化研究所复杂系统认知与决策智能重点实验室）；School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学前沿交叉科学学院）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Academy（中关村学院）；Zhongguancun Institute of Artificial Intelligence（中关村人工智能研究院）；Meituan（美团）
AI PERSONA: Towards Life-long Personalization of LLMs
OPPO AI Center（OPPO AI中心）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Beihang University（北京航空航天大学）；Tsinghua University（清华大学）；Guangdong University of Technology（广东工业大学）
Using Large Language Models to Create AI Personas for Replication, Generalization and Prediction of Media Effects: An Empirical Test of 133 Published Experimental Research Findings
PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation
University of Liverpool（利物浦大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University College London（伦敦大学学院）；Xi'an Jiaotong-Liverpool University（西安交通大学-利物浦大学）；Chinese Academy of Sciences（中国科学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
ReMe: Scaffolding Personalized Cognitive Training via Controllable LLM-Mediated Conversations
Microsoft Research（微软研究院）；Department of Geriatric Psychiatry, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属上海市精神卫生中心老年精神科）
Transformative Influence of LLM and AI Tools in Student Social Media Engagement: Analyzing Personalization, Communication Efficiency, and Collaborative Learning
PERCEIVE: A Benchmark for Personalized Emotion and Communication Behavior Understanding on Social Media
School of Computer and Information Technology, Shanxi University, China（山西大学计算机与信息学院）；Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, China（教育部计算智能与中文信息处理重点实验室，山西大学，中国）；Joint Laboratory of Tourism Big Data in Shanxi Province, China（山西省旅游大数据联合实验室）
