{"total":19,"rows":[{"id":"2604.20779","title":"SWE-chat: Coding Agent Interactions From Real Users in the Wild","created":"2026-04-22","cited_by_count":43,"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":"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":"2608.04205","title":"MatrAIx: Simulating the World with 8.3 Billion Persona Agents","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"id":"2608.12253","title":"One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2609.12191","title":"GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents","created":"2026-09-10","cited_by_count":3,"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":"2604.23815","title":"DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute","created":"2026-04-26","cited_by_count":1,"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":"2606.11520","title":"ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories","created":"2026-06-09","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":"2606.12969","title":"Multi-Modal Agents for Power Distribution Defect Detection: An Evaluation of Foundation Models","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2607.02975","title":"Where Knowledge and Authority Sit Changes What an Agent Benchmark Can Resolve","created":"2026-07-03","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":"2610.09484","title":"MIMESIS: Learning User Simulators as Training Environments for Interactive Agents","created":"2026-10-07","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":"2610.16067","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"},{"id":"2610.16523","title":"EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}