arxiv:2609.20784
Zhengxi Lu
LZXzju
AI & ML interests
None yet
Recent Activity
authored a paper about 8 hours ago
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning authored a paper 2 days ago
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents commentedon a paper 3 days ago
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement LearningOrganizations
arxiv:2609.17653
arxiv:2608.31119
arxiv:2608.27448
arxiv:2608.23318
arxiv:2608.06197
arxiv:2608.05987
arxiv:2608.00782
arxiv:2607.28590
arxiv:2607.26784
arxiv:2607.14777
arxiv:2606.26790
arxiv:2605.28534
arxiv:2605.22177
arxiv:2605.15155
arxiv:2605.06130
arxiv:2604.13822
arxiv:2604.14113
arxiv:2604.08455
arxiv:2604.02268
arxiv:2603.15611
arxiv:2602.06075
arxiv:2509.11543
arxiv:2509.06477
arxiv:2508.15144
arxiv:2508.05615
arxiv:2507.15846
arxiv:2503.21620
