D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents Paper • 2509.21799 • Published Sep 26, 2025 • 8 • 2
UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios Paper • 2509.21766 • Published Sep 26, 2025 • 23 • 2
AdaR1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization Paper • 2504.21659 • Published Apr 30, 2025 • 14 • 1