Sheldon Yu

1. Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
   2026/07/20 by Sheldon Yu, Tong Yu, Xunyi Jiang +6
   #cs.AI
2. RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts
   2026/07/20 by Yuxin Xiong, Xunyi Jiang, Rohan Surana +8
   #cs.LG #cs.AI
3. Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability
   2026/07/29 by Sizhe Zhou, Sheldon Yu, Hui Wei +8
   Computer Science · #cs.AI #cs.CL