AI.info

Yihong Zhuang

Explore Yihong Zhuang on AI.info.

• RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
• Training-Trajectory-Aware Token Selection
• Falcon: A Comprehensive Chinese Text-to-SQL Benchmark for Enterprise-Grade Evaluation