{"total":52,"rows":[{"id":"2601.07110","title":"The Need for a Socially-Grounded Persona Framework for User Simulation","created":"2026-01-12","cited_by_count":15,"area":null},{"id":"2605.03202","title":"Stop Automating Peer Review Without Rigorous Evaluation","created":"2026-05-04","cited_by_count":14,"area":null},{"id":"2601.06407","title":"Value of Information: A Framework for Human-Agent Communication","created":"2026-01-10","cited_by_count":12,"area":"agents"},{"id":"2604.08362","title":"Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces","created":"2026-04-09","cited_by_count":9,"area":null},{"id":"2601.03154","title":"Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2605.10659","title":"When Can Digital Personas Reliably Approximate Human Survey Findings?","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2602.22752","title":"Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2608.05583","title":"The Judgment-Consequence Gap: LLM Moral Reasoning in Healthcare Decisions","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2601.06403","title":"Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding","created":"2026-01-10","cited_by_count":2,"area":null},{"id":"2602.00685","title":"HumanStudy-Bench: Towards AI Agent Design for Participant Simulation","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2604.04468","title":"What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2605.25680","title":"Simulating Human Memory with Language Models","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2607.15277","title":"Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models","created":"2026-07-16","cited_by_count":2,"area":"lr"},{"id":"2609.02526","title":"When Persona Attributes Improve Population Alignment in Large Language Models","created":"2026-09-02","cited_by_count":2,"area":null},{"id":"2602.11650","title":"Investigating Learner-Aware Design of LLM-Generated Educational Feedback","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.17222","title":"Decoding the Human Factor: High Fidelity Behavioral Prediction for Strategic Foresight","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.19002","title":"RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulation","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.11840","title":"Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation","created":"2026-04-12","cited_by_count":1,"area":"agents"},{"id":"2605.17079","title":"Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench","created":"2026-05-16","cited_by_count":1,"area":"lr"},{"id":"2605.29062","title":"Bosses, Kings, and the Commons: Cooperation Under Power Asymmetry in LLM Societies","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.09351","title":"In-Context Learning for the Imputation of Public Opinion Data with Large Language Models","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.09833","title":"CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.24162","title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.18310","title":"Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2608.29455","title":"Item-Mean Surrogates: Why Richer Persona Data Fail to Improve LLMs as Human Surrogates","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2601.03546","title":"Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2605.00197","title":"The $\\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.12147","title":"PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.15473","title":"Validated Hypotheses as a Lens for Human-Likeness Evaluation in AI Agents","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2605.27395","title":"Informing AI Policy Assessment using Large-Scale Simulation of Interventions","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.02798","title":"BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.06266","title":"From Self to Other: Evaluating Demographic Perspective-Taking in LLM Hate Speech Annotation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.14715","title":"MiroBench: Benchmarking Realism in Agentic Simulation of Real-world Discussions","created":"2026-05-10","cited_by_count":0,"area":"agents"},{"id":"2606.16415","title":"Posterior Twins: Distributional Behavioral Simulation for Enterprise Decisions","created":"2026-06-15","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":"2607.08625","title":"The complexities of patient-centred conversational artificial intelligence","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.01868","title":"No One Wins in Nuclear War: A Social Simulation of Military Decision-making","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.19689","title":"Rethinking the Evaluation and Optimization of LLM-Based Social Simulation","created":"2026-08-20","cited_by_count":0,"area":"lr"},{"id":"2608.28182","title":"Benchmarking large language model agent societies against human behavioural distributions","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2608.28399","title":"RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.00565","title":"Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.09882","title":"Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.21259","title":"CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25066","title":"Understanding Reliability in LLM-based Human Behavior Simulation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.30030","title":"Artificial Societies Benchmark: A Validation Framework for Synthetic Research","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.33155","title":"Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35376","title":"How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36278","title":"Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37853","title":"AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02460","title":"CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03998","title":"Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04246","title":"Benchmarking Psychological Dynamics in Generative Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"}],"next_cursor":null}