{"total":30,"rows":[{"id":"2605.13841","title":"EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents","created":"2026-05-13","cited_by_count":18,"area":null},{"id":"2606.14199","title":"OdysSim: Building Foundation Models for Human Behavior Simulation","created":"2026-06-12","cited_by_count":13,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2606.19336","title":"Learning User Simulators with Turing Rewards","created":"2026-06-17","cited_by_count":7,"area":null},{"id":"2605.07847","title":"Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2605.25680","title":"Simulating Human Memory with Language Models","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.11079","title":"VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2605.05700","title":"An Empirical Study of Proactive Coding Assistants in Real-World Software Development","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.21363","title":"\"I Didn't Make the Micro Decisions\": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration","created":"2026-05-20","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":"2606.20138","title":"Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.06993","title":"Large Behavior Model: A Promptable Digital Twin of the Retail Customer","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.09420","title":"Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2604.02315","title":"Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models","created":"2026-04-02","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":"2607.02464","title":"Will Scaling Improve Social Simulation with LLMs?","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.18768","title":"Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.30033","title":"\"Act Like a 5th Grader\" is Not Enough: Bounding Knowledge in LLM-Based User Simulators","created":"2026-08-30","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":"2609.01257","title":"Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.07305","title":"Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.16093","title":"Evaluating Open-Weight E-Commerce Agents with Environment-Grounded Verification","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.22607","title":"Pretrained Persona Mixture Models and Tandem Models for Human Simulation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.36614","title":"Selective Elicitation as a Commercial Influence Channel: A Reproducible Synthetic Shopping-Agent Stress Test","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":"2610.12023","title":"InterviewPlayground: A Validated Simulation Environment for Evaluating AI Interviewers","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13617","title":"Training User Simulators with Latent Intrinsic Feedback","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17670","title":"Cowork-Gym: Synthesizing Interactive Work Environments at Scale","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}