Qinglin Su
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1Crypto×1
Frequent co-authors
Research Timeline
2026
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIcs.CRRecentJun 2, 2026
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
Xian Qi Loye, Qinglin Su, Zhexin Zhang, Shiyao Cui +4 more
The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.
View →