{"total":54,"rows":[{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431,"area":"agents"},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109,"area":"lr"},{"id":"2410.13648","title":"SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs","created":"2024-10-17","cited_by_count":57,"area":null},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51,"area":"alignment"},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2511.01805","title":"Accumulating Context Changes the Beliefs of Language Models","created":"2025-11-03","cited_by_count":28,"area":null},{"id":"2502.20502","title":"On Benchmarking Human-Like Intelligence in Machines","created":"2025-02-27","cited_by_count":25,"area":null},{"id":"2504.09689","title":"EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety","created":"2025-04-13","cited_by_count":21,"area":null},{"id":"2407.04503","title":"When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings","created":"2024-07-05","cited_by_count":17,"area":null},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2505.17968","title":"Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2502.17701","title":"From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMs","created":"2025-02-24","cited_by_count":12,"area":null},{"id":"2509.25609","title":"A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments","created":"2025-09-30","cited_by_count":12,"area":"agents"},{"id":"2503.13401","title":"Levels of Analysis for Large Language Models","created":"2025-03-17","cited_by_count":10,"area":null},{"id":"2508.14146","title":"MMReview: A Multidisciplinary and Multimodal Benchmark for LLM-Based Peer Review Automation","created":"2025-08-19","cited_by_count":10,"area":null},{"id":"2602.06286","title":"When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs","created":"2026-02-06","cited_by_count":10,"area":"agents"},{"id":"2410.18066","title":"The Double-Edged Sword of Behavioral Responses in Strategic Classification: Theory and User Studies","created":"2024-10-23","cited_by_count":9,"area":null},{"id":"2502.00313","title":"Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values","created":"2025-02-01","cited_by_count":9,"area":"alignment"},{"id":"2604.02485","title":"Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models","created":"2026-04-02","cited_by_count":9,"area":"lr"},{"id":"2510.19687","title":"Are Large Language Models Sensitive to the Motives Behind Communication?","created":"2025-10-22","cited_by_count":8,"area":null},{"id":"2502.12149","title":"HARBOR: Exploring Persona Dynamics in Multi-Agent Competition","created":"2025-02-17","cited_by_count":6,"area":"agents"},{"id":"2505.11615","title":"Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations","created":"2025-05-16","cited_by_count":6,"area":"mechinterp"},{"id":"2408.09176","title":"Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making","created":"2024-08-17","cited_by_count":5,"area":"lr"},{"id":"2505.11584","title":"LLM Agents Are Hypersensitive to Nudges","created":"2025-05-16","cited_by_count":5,"area":"agents"},{"id":"2603.10396","title":"Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities","created":"2026-03-11","cited_by_count":5,"area":null},{"id":"2605.08556","title":"Can Revealed Preferences Clarify LLM Alignment and Steering?","created":"2026-05-08","cited_by_count":5,"area":"alignment"},{"id":"2510.10930","title":"Evaluating Language Models' Evaluations of Games","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2603.17218","title":"Alignment Makes Language Models Normative, Not Descriptive","created":"2026-03-17","cited_by_count":4,"area":"alignment"},{"id":"2503.10248","title":"LLM Agents Display Human Biases but Exhibit Distinct Learning Patterns","created":"2025-03-13","cited_by_count":3,"area":"agents"},{"id":"2602.09802","title":"Would a Large Language Model Pay Extra for a View? Inferring Willingness to Pay from Subjective Choices","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2604.17730","title":"MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2501.10476","title":"Revisiting Rogers' Paradox in the Context of Human-AI Interaction","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2509.22537","title":"The Emergence of Altruism in Large-Language-Model Agents Society","created":"2025-09-26","cited_by_count":2,"area":"agents"},{"id":"2511.21218","title":"Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2601.18027","title":"Sentipolis: Emotion-Aware Agents for Social Simulations","created":"2026-01-25","cited_by_count":2,"area":"agents"},{"id":"2606.17657","title":"Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2503.14004","title":"Predicting Human Choice Between Textually Described Lotteries","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2506.17367","title":"Cash or Comfort? How LLMs Value Your Inconvenience","created":"2025-06-20","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":"2608.18081","title":"Position: Behavioral Systems Require Behavioral Tests","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2601.11049","title":"Predicting Biased Human Decision-Making with Large Language Models in Conversational Settings","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.00769","title":"Eliciting Trustworthiness Priors of Large Language Models via Economic Games","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.05597","title":"Emulating Aggregate Human Choice Behavior and Biases with GPT Conversational Agents","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2605.01164","title":"LLMs Should Not Yet Be Credited with Decision Explanation","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.06196","title":"The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.18005","title":"LLM Consumer Behavior Theory: Foundations of a Novel Research Field","created":"2026-06-16","cited_by_count":0,"area":"agents"},{"id":"2607.02464","title":"Will Scaling Improve Social Simulation with LLMs?","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.19965","title":"Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.00679","title":"Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allow","created":"2026-09-30","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"},{"id":"2610.05461","title":"AI Safety via Debate is Compromised by Cognitive Biases","created":"2026-10-04","cited_by_count":0,"area":"alignment"},{"id":"2610.18515","title":"A Global View of How LLMs Value Human Time","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}