Cite
Notes
Only stored in your browser.
Attribution
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
arXiv 2026
DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution
The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes
from 3 papers
Shengda Fan
Yankai Lin
Ge Liu
Haotian Chen
Hongyu Lu
Jingwen Chen
Shenzhi Yang
Shuqi Ye
Siqi Zhu
Weiye Shi