UCLA Scalable Analytics Institute

AI & ML interests

None defined yet.

Recent Activity

willhx  submitted a paper 23 days ago

ACLArena: Agent Continue Learning in Multi-stage Post-training

willhx  authored a paper 4 months ago

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

willhx  authored a paper 4 months ago

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

View all activity

Papers

ACLArena: Agent Continue Learning in Multi-stage Post-training

View all Papers

Team members 6