{"total":99,"rows":[{"id":"2402.10811","title":"Quantifying the Persona Effect in LLM Simulations","created":"2024-02-16","cited_by_count":169,"area":null},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2404.01230","title":"LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models","created":"2024-04-01","cited_by_count":99,"area":"lr"},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71,"area":null},{"id":"2402.17385","title":"Determinants of LLM-assisted Decision-Making","created":"2024-02-27","cited_by_count":56,"area":null},{"id":"2406.12934","title":"Current state of LLM Risks and AI Guardrails","created":"2024-06-16","cited_by_count":46,"area":"safety"},{"id":"2406.17232","title":"Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks","created":"2024-06-25","cited_by_count":39,"area":"agents"},{"id":"2404.06711","title":"MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education","created":"2024-04-10","cited_by_count":37,"area":null},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2502.08395","title":"IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance","created":"2025-02-12","cited_by_count":26,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2412.06681","title":"Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework","created":"2024-12-09","cited_by_count":19,"area":"agents"},{"id":"2509.14034","title":"Enhancing Multi-Agent Debate System Performance via Confidence Expression","created":"2025-09-17","cited_by_count":19,"area":"agents"},{"id":"2501.14844","title":"Unmasking Conversational Bias in AI Multiagent Systems","created":"2025-01-24","cited_by_count":17,"area":null},{"id":"2602.14299","title":"Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook","created":"2026-02-15","cited_by_count":15,"area":"agents"},{"id":"2407.18008","title":"GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2404.01332","title":"Explaining Large Language Models Decisions Using Shapley Values","created":"2024-03-29","cited_by_count":12,"area":null},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12,"area":null},{"id":"2412.15291","title":"A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2403.18680","title":"Non-Linear Inference Time Intervention: Improving LLM Truthfulness","created":"2024-03-27","cited_by_count":9,"area":null},{"id":"2503.01513","title":"Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2503.02457","title":"Don't Get Too Excited -- Eliciting Emotions in LLMs","created":"2025-03-04","cited_by_count":9,"area":null},{"id":"2507.00657","title":"Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity","created":"2025-07-01","cited_by_count":9,"area":"agents"},{"id":"2410.13517","title":"Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2602.11328","title":"Evaluating Alignment of Behavioral Dispositions in LLMs","created":"2026-02-11","cited_by_count":7,"area":"alignment"},{"id":"2510.25110","title":"DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents","created":"2025-10-29","cited_by_count":6,"area":"agents"},{"id":"2606.30571","title":"Attractor States Emerge in Multi-Turn LLM Conversations","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2409.01907","title":"Focus Agent: LLM-Powered Virtual Focus Group","created":"2024-09-03","cited_by_count":4,"area":"agents"},{"id":"2402.14889","title":"COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2411.03397","title":"SAUCE: Synchronous and Asynchronous User-Customizable Environment for Multi-Agent LLM Interaction","created":"2024-11-05","cited_by_count":3,"area":"agents"},{"id":"2503.09311","title":"Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactions","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2506.11825","title":"Revealing Political Bias in LLMs through Structured Multi-Agent Debate","created":"2025-06-13","cited_by_count":3,"area":"agents"},{"id":"2510.13011","title":"Deliberate Lab: A Platform for Real-Time Human-AI Social Experiments","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2604.11721","title":"Evaluating Cooperation in LLM Social Groups through Elected Leadership","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2503.16505","title":"Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2503.20182","title":"Beyond BFI: The CSI for Enhanced Reliability and Validity in Evaluating LLM Personality Traits","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2505.20120","title":"Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2508.18600","title":"Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics","created":"2025-08-26","cited_by_count":2,"area":"agents"},{"id":"2509.06858","title":"Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2510.05611","title":"MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction","created":"2025-10-07","cited_by_count":2,"area":"agents"},{"id":"2510.06307","title":"Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.10943","title":"The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2512.07665","title":"Reliable agent engineering should integrate machine-compatible organizational principles","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2601.05403","title":"Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2602.19844","title":"LLM-enabled Applications Require System-Level Threat Monitoring","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2605.07896","title":"What if AI systems weren't chatbots?","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.15343","title":"Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation","created":"2026-05-14","cited_by_count":2,"area":"agents"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2607.03695","title":"Social Networks of LLM Agents","created":"2026-07-04","cited_by_count":2,"area":"agents"},{"id":"2608.10186","title":"The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2403.14298","title":"From Perils to Possibilities: Understanding how Human (and AI) Biases affect Online Fora","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2409.04043","title":"Towards Safer Online Spaces: Simulating and Assessing Intervention Strategies for Eating Disorder Discussions","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2410.06845","title":"MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders","created":"2024-10-09","cited_by_count":1,"area":"synth"},{"id":"2502.11349","title":"Biases in Edge Language Models: Detection, Analysis, and Mitigation","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2504.04872","title":"Simulating Persuasive Dialogues on Meat Reduction with Generative Agents","created":"2025-04-07","cited_by_count":1,"area":"agents"},{"id":"2504.17052","title":"PReSS: An Automated Black-Box Framework for Evaluating Political Stance Stability in LLMs","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2506.01524","title":"V-VAE: A Variational Auto Encoding Framework Towards Fine-Grained Control over Human-Like Chat","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.21587","title":"A Cross-Cultural Comparison of LLM-based Public Opinion Simulation: Evaluating Chinese and U.S. Models on Diverse Societies","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2508.17825","title":"FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2510.13884","title":"Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2602.13280","title":"BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2605.28369","title":"CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict","created":"2026-05-27","cited_by_count":1,"area":"agents"},{"id":"2607.27512","title":"Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2505.01754","title":"Unraveling Media Perspectives: A Comprehensive Methodology Combining Large Language Models, Topic Modeling, Sentiment Analysis, and Ontology Learning to Analyse Media Bias","created":"2025-05-03","cited_by_count":0,"area":null},{"id":"2505.19121","title":"Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2506.11798","title":"Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2508.08265","title":"TurQUaz at CheckThat! 2025: Debating Large Language Models for Scientific Web Discourse Detection","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2511.17256","title":"Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysis","created":"2025-11-21","cited_by_count":0,"area":"alignment"},{"id":"2512.17060","title":"On the Role of Contextual Information and Ego States in LLM Agent Behavior for Transactional Analysis Dialogues","created":"2025-12-18","cited_by_count":0,"area":"agents"},{"id":"2604.02230","title":"Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.11312","title":"Collective Opinion Dynamics in Structured LLM Populations","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.12545","title":"Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.20131","title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.23786","title":"FAIR_XAI: Improving Multimodal Foundation Model Fairness via Explainability for Wellbeing Assessment","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.08321","title":"LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.12411","title":"Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.15768","title":"ALSO: Adversarial Online Strategy Optimization for Social Agents","created":"2026-05-15","cited_by_count":0,"area":"agents"},{"id":"2605.19141","title":"GRASP: Deterministic argument ranking in interaction graphs","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.01584","title":"Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2606.14209","title":"Detecting undisclosed LLM-generated content in parliamentary texts","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.02464","title":"Will Scaling Improve Social Simulation with LLMs?","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.20429","title":"More Is Not More: What Matters for Diversity in LLM Opinions?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.27232","title":"Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.03722","title":"When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Diagnostic for Machine Collectives","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.20355","title":"ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.29803","title":"Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.07573","title":"From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.13470","title":"OrchSLM: Probing the Dynamics of Small Language Model Orchestration","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.15849","title":"Before You Poll with LLMs: A Deliberative Diagnostic Framework","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.16189","title":"Position: AI Is Not Ready for Strategic Conflicts","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.21997","title":"Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.38964","title":"When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.03095","title":"Peer Influence across Heterogeneous AI Models","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}