{"total":97,"rows":[{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2410.16464","title":"Beyond Browsing: API-Based Web Agents","created":"2024-10-21","cited_by_count":78,"area":"agents"},{"id":"2411.05403","title":"Benchmarking Distributional Alignment of Large Language Models","created":"2024-11-08","cited_by_count":61,"area":"alignment"},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54,"area":"agents"},{"id":"2602.06052","title":"A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents","created":"2026-01-14","cited_by_count":44,"area":"agents"},{"id":"2505.17818","title":"PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2505.00753","title":"LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey","created":"2025-05-01","cited_by_count":29,"area":"agents"},{"id":"2602.03794","title":"Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity","created":"2026-02-03","cited_by_count":29,"area":"agents"},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27,"area":null},{"id":"2412.00804","title":"Examining Identity Drift in Conversations of LLM Agents","created":"2024-12-01","cited_by_count":25,"area":"agents"},{"id":"2501.15427","title":"OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas","created":"2025-01-26","cited_by_count":25,"area":null},{"id":"2505.21116","title":"Creativity in LLM-based Multi-Agent Systems: A Survey","created":"2025-05-27","cited_by_count":23,"area":"agents"},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2502.14642","title":"How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation","created":"2025-02-20","cited_by_count":22,"area":null},{"id":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2505.02847","title":"Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models","created":"2025-05-01","cited_by_count":21,"area":"agents"},{"id":"2509.10127","title":"Population-Aligned Persona Generation for LLM-based Social Simulation","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2605.20204","title":"RealUserSim: Bridging the Reality Gap in Agent Benchmarking via Grounded User Simulation","created":"2026-04-07","cited_by_count":12,"area":"agents"},{"id":"2409.06820","title":"PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation","created":"2024-09-10","cited_by_count":10,"area":null},{"id":"2510.04491","title":"Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents","created":"2025-10-06","cited_by_count":10,"area":null},{"id":"2502.12988","title":"Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2506.09420","title":"A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy","created":"2025-06-11","cited_by_count":9,"area":"agents"},{"id":"2505.07313","title":"Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study","created":"2025-05-12","cited_by_count":8,"area":"lr"},{"id":"2506.17434","title":"Resource Rational Contractualism Should Guide AI Alignment","created":"2025-06-20","cited_by_count":8,"area":null},{"id":"2507.09788","title":"TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit","created":"2025-07-13","cited_by_count":7,"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":"2504.16946","title":"MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation","created":"2025-04-18","cited_by_count":5,"area":"agents"},{"id":"2511.03235","title":"From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers","created":"2025-11-05","cited_by_count":5,"area":null},{"id":"2512.09756","title":"MOA: Multi-Objective Alignment for Role-Playing Agents","created":"2025-12-10","cited_by_count":5,"area":null},{"id":"2409.00262","title":"DiverseDialogue: A Methodology for Designing Chatbots with Human-Like Diversity","created":"2024-08-30","cited_by_count":4,"area":null},{"id":"2508.20186","title":"AI Propaganda factories with language models","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2511.08565","title":"Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models","created":"2025-11-11","cited_by_count":4,"area":null},{"id":"2512.06867","title":"Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?","created":"2025-12-07","cited_by_count":4,"area":"lr"},{"id":"2601.16356","title":"The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes","created":"2026-01-22","cited_by_count":4,"area":"agents"},{"id":"2605.20506","title":"Reinforcing Human Behavior Simulation via Verbal Feedback","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2502.11423","title":"Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2504.06460","title":"Can LLMs Simulate Personas with Reversed Performance? A Systematic Investigation for Counterfactual Instruction Following in Math Reasoning Context","created":"2025-04-08","cited_by_count":3,"area":"lr"},{"id":"2510.06370","title":"EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences","created":"2025-10-07","cited_by_count":3,"area":"alignment"},{"id":"2510.11290","title":"Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics","created":"2025-10-13","cited_by_count":3,"area":"agents"},{"id":"2602.06357","title":"LLM-SAA: LLM-persona Generated Distributions for Decision-making","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2603.02876","title":"Eval4Sim: An Evaluation Framework for Persona Simulation","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2603.25620","title":"PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency","created":"2026-03-26","cited_by_count":3,"area":"agents"},{"id":"2605.17044","title":"PersonaArena: Dynamic Simulation for Evaluating and Enhancing Persona-Level Role-Playing in Large Language Models","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.01552","title":"RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2501.12651","title":"The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2503.22115","title":"Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories","created":"2025-03-28","cited_by_count":2,"area":"alignment"},{"id":"2510.07488","title":"Can Lessons From Human Teams Be Applied to Multi-Agent Systems? The Role of Structure, Diversity, and Interaction Dynamics","created":"2025-10-08","cited_by_count":2,"area":"agents"},{"id":"2511.17467","title":"PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2601.04716","title":"Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes","created":"2026-01-08","cited_by_count":2,"area":"agents"},{"id":"2602.23729","title":"From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning","created":"2026-02-27","cited_by_count":2,"area":"lr"},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2606.13608","title":"AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2502.11197","title":"CSP: A Simulator For Multi-Agent Ranking Competitions","created":"2025-02-16","cited_by_count":1,"area":"agents"},{"id":"2502.20504","title":"A Thousand Words or An Image: Studying the Influence of Persona Modality in Multimodal LLMs","created":"2025-02-27","cited_by_count":1,"area":"mllm"},{"id":"2505.21458","title":"Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance","created":"2025-05-27","cited_by_count":1,"area":"lr"},{"id":"2506.12486","title":"DinoCompanion: An Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2601.15671","title":"StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2604.00979","title":"Dual Optimal: Make Your LLM Peer-like with Dignity","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2606.01736","title":"Argument Collapse: LLMs Flatten Long-Form Public Debate","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2608.11236","title":"TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.13564","title":"Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2503.15497","title":"The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study","created":"2025-01-15","cited_by_count":0,"area":"agents"},{"id":"2505.24255","title":"Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games","created":"2025-05-30","cited_by_count":0,"area":"lr"},{"id":"2509.15447","title":"PILOT: Steering Synthetic Data Generation with Psychological & Linguistic Output Targeting","created":"2025-09-18","cited_by_count":0,"area":"synth"},{"id":"2511.20200","title":"Interactive AI NPCs Powered by LLMs: Technical Report for the CPDC Challenge 2025","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2601.06158","title":"PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2603.28351","title":"Not All Subjectivity Is the Same! Defining Desiderata for the Evaluation of Subjectivity in NLP","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.08986","title":"PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.09682","title":"Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN","created":"2026-04-03","cited_by_count":0,"area":"agents"},{"id":"2604.19278","title":"Explicit Trait Inference for Multi-Agent Coordination","created":"2026-04-21","cited_by_count":0,"area":"agents"},{"id":"2605.28969","title":"Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.06388","title":"Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2606.14314","title":"Communication Policy Evolution for Proactive LLM Agents","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2607.05477","title":"Decision Protocols in Multi-Agent Large Language Model Conversations","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.18566","title":"The Story Shapes the Agent: Narrative Priors in LLM Behavior","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.00007","title":"MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents","created":"2026-06-10","cited_by_count":0,"area":"agents"},{"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":"2609.00453","title":"mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00608","title":"Investigating Assistant Bias in LLM User Simulators Using a Role Vector","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01615","title":"Prompt-Space Meta-Learning Does Not Transfer Across Users: A Frozen-LLM Negative Result","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2609.02890","title":"Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2609.13637","title":"Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.16667","title":"ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.34372","title":"PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34571","title":"PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations","created":"2026-09-28","cited_by_count":0,"area":null},{"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":"2609.37853","title":"AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38555","title":"Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributions","created":"2026-09-29","cited_by_count":0,"area":"alignment"},{"id":"2609.39882","title":"LLM Persona Unlearning","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.03356","title":"ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World Models","created":"2026-10-02","cited_by_count":0,"area":"wm"},{"id":"2610.04379","title":"AgentPersonaBench: Benchmarking Persona-Driven User Simulation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04676","title":"Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.12975","title":"SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.15163","title":"Sanzaru: Benchmarking Protocol Formation under Epistemic & Communication Asymmetry","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16498","title":"From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}