On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this integration. Gradient corrections directly constrain parameter updates under plain SGD. With optimizers such as AdamW, however, momentum, adaptive scaling, and weight de...
Tao-Jie Zhu, Jing Jin, Yuan Xia et al.· 0 citations
The findings support on-policy distillation as an effective warmup for agentic RLVR and identify initial reward discovery as a mechanism that can contribute to the observed acceleration.
Yi-Tong Qiao, Tian-Tian He, Lei Liu et al.· arXiv.org· 0 citations
In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements referenced in a clinical query. Even when database retrieval succeeds, clinical agents can overlook such discrepancies and return plausible but unsupported answers. We intro...
Yi-Tong Qiao, Yan-Cheng Jin, Lei Liu et al.· arXiv.org· 0 citations
It is demonstrated that verifying evidential support before submission can make diagnostic decisions more reliable, and decouples diagnosis generation from submission through an offline Contrastive Diagnostic Wiki and three online control stages, namely observation management, proposal and witness verification, and dia...
Ke-Hua Feng, Yun-Sheng Lu, Yi-Tong Qiao et al.· 0 citations
ConRub-Med is introduced to preserve useful distinctions as rubric feedback moves from construction to policy optimization, and ranks first on six of nine benchmarks and achieves the highest medical and generalization averages.
Taojie Zhu, Yuan Xia, Tao Sun et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.