{"total":18,"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":"2601.17087","title":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","created":"2026-01-23","cited_by_count":40,"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":"2601.08118","title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness","created":"2026-01-13","cited_by_count":7,"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":"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":"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":"2606.14314","title":"Communication Policy Evolution for Proactive LLM Agents","created":"2026-06-12","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":"2608.08995","title":"Muscle Memory for Agents: Compile not Merely Retrieve","created":"2026-08-10","cited_by_count":0,"area":"agents"},{"id":"2608.09939","title":"How to Dogfood Your AI Chat Agent: A Three-Layer Evaluation Framework with Goal-Directed NPC Simulation","created":"2026-06-08","cited_by_count":0,"area":"agents"},{"id":"2609.30137","title":"Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale","created":"2026-09-24","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":"2610.02563","title":"OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game Engine","created":"2026-10-01","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":"2610.16067","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"}],"next_cursor":null}