AI.info

Zhengxi Lu

Explore Zhengxi Lu on AI.info.

• PaperGym: Rubric-Centered Evolution for Research-Plan Generation
• TTPO: Test-Time Policy Optimization
• Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning
• EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
• VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation