Cite
Notes
Only stored in your browser.
Attribution
Behavior Knowledge Merge in Reinforced Agentic Models
arXiv 2026
CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
arXiv 2025
from 3 papers
Dachuan Shi
Xiangchi Yuan
Wen Xiao
Abedelkadir Asi
Chunhui Zhang
Hanlin Zhu
researcher
Kejing Xia
Keying Li
Leyan Pan
Shenglong Yao