2 papers
cs.LG2026
Reproducible macroscopic dynamics in a closed-loop human-AI learning system
Minlin Wu, Xu Fang, Yicheng Zhang +2
Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adaptive-tutoring histories, we de…
cs.AI2026
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…