Zhicheng Cai
Aiolus-X
AI & ML interests
LLM&Agentic RL
Recent Activity
authored a paper about 23 hours ago
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization authored a paper about 23 hours ago
FLEX: Continuous Agent Evolution via Forward Learning from Experience authored a paper about 23 hours ago
Enigmata: Scaling Logical Reasoning in Large Language Models with
Synthetic Verifiable PuzzlesOrganizations
None yet