Post-Training Leaves Behavioral Shadows on Unrelated Decisions Paper • 2609.29233 • Published 7 days ago • 262
DataFlex-RL: An Evaluation Platform for RLVR Data Policies Paper • 2609.06107 • Published 26 days ago • 165
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published 17 days ago • 250