JevGPT: Thinking Fast and Slow in Autonomous Research Paper • 2610.18272 • Published 15 days ago • 41
ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling Paper • 2610.15166 • Published 18 days ago • 85
PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems Paper • 2610.13989 • Published Sep 26 • 11
AutoEnvScaling: Automating the Data Flywheel with Terminal Agents Paper • 2610.14163 • Published 19 days ago • 13