Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
Miteto Wei, Xiaohan Wang, Zehao Chen +7
On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teacher-misaligned prefixes wher…
cs.AI2026
ATLAS: Dual-Horizon Diagnostic Evaluation for Tool-Use Agents in Meituan Xiaotua
Wei Chen, Peilun Zhou, Zhaoyu Hu +8
LLM-based assistants on web-scale service platforms increasingly address local-service needs through multi-step planning and tool use. Under dynamic business conditions and evolvin…