TIANSHI XU's picture

2

TIANSHI XU

TianshiXu

1907FB

AI & ML interests

Agentic RL, Efficient AI

Recent Activity

upvoted a paper 1 day ago

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

updated a dataset about 2 months ago

TianshiXu/docker

updated a dataset 2 months ago

TianshiXu/docker

View all activity

Organizations

None yet

upvoted a paper 1 day ago

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

Paper • 2605.22166 • Published 5 days ago • 1

upvoted a paper 3 months ago

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning

Paper • 2601.15141 • Published Jan 21 • 2