RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published 5 days ago • 203
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published 12 days ago • 246
Reinforcing Multimodal Reasoning Against Visual Degradation Paper • 2605.09262 • Published May 10 • 6
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification Paper • 2605.09269 • Published May 10 • 5
Reinforcing Multimodal Reasoning Against Visual Degradation Paper • 2605.09262 • Published May 10 • 6
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification Paper • 2605.09269 • Published May 10 • 5
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification Paper • 2605.09269 • Published May 10 • 5