Simon Yu ✈️ EMNLP2026
@simon_ycl
Building Self-improvement system (Shepherd, SPADE) | 3rd Year PhD, supervised by @shi_weiyan | intern in @MSFTResearch | Prev Student @EdinburghNLP
979 Following 922 Followers
Recursive self-improvement needs agents that can build their own training environments. But researchers still part of the loop, making it hard to scale.
We introduce AutoEnvScaling, which turns Data Flywheel into a terminal task: a proposer agent builds complete Harbor tasks and sandbox. It builds just like human researchers. This enables self-play RL for terminal agents: one model improves as both builder and solver, without human-in-the-loop.
Show more
