Showing cs.AIShow all
2 papers · 1 filter
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…
cs.AI2026
LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systems
Zhiyuan Wang, Aniri, Tianlong Chen +4
Foundation models often generate unreliable answers, while heuristic uncertainty estimators fail to fully distinguish correct from incorrect outputs, causing users to accept errone…