ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping Paper • 2510.08457 • Published Oct 9 • 12
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning Paper • 2509.02544 • Published Sep 2 • 124
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting Paper • 2505.18822 • Published May 24 • 15
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs Paper • 2504.11536 • Published Apr 15 • 63
UI-TARS: Pioneering Automated GUI Interaction with Native Agents Paper • 2501.12326 • Published Jan 21 • 65