{"total":21,"rows":[{"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":"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":"2606.30573","title":"SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions","created":"2026-06-29","cited_by_count":11,"area":"agents"},{"id":"2605.12894","title":"Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents","created":"2026-05-13","cited_by_count":10,"area":"agents"},{"id":"2607.20536","title":"AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2602.15219","title":"Multi-Agent Home Energy Management Assistant","created":"2026-02-16","cited_by_count":3,"area":"agents"},{"id":"2602.22523","title":"Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents","created":"2026-02-26","cited_by_count":2,"area":"agents"},{"id":"2604.06452","title":"Learning to Interrupt in Language-based Multi-agent Communication","created":"2026-04-07","cited_by_count":2,"area":"agents"},{"id":"2606.20708","title":"Simulated Customers Never Walk Away: Decision Fidelity of LLM User Simulators Measured Against Real Purchase Outcomes","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2606.01815","title":"CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2608.00794","title":"Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.27818","title":"AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics","created":"2026-08-28","cited_by_count":1,"area":"agents"},{"id":"2609.00982","title":"Disclosure-Gated User Simulation for Companion-Agent Evaluation","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2609.38043","title":"UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2608.14093","title":"AppLooper: An Agentic Application Engineering Loop for Accountable Release with Virtual-User Feedback","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2609.26204","title":"WatchPoint: Executable User Feedback for Real-World Agentic Web Development","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2609.32092","title":"On Evaluating and Improving Conversational Agents in Production","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2610.10988","title":"Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.13989","title":"PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.16067","title":"When Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.16155","title":"Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}