MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model Paper • 2610.37175 • Published 10 days ago • 7
Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents Paper • 2610.18784 • Published 23 days ago • 119
ReSI: Recursive Safety Improvement toward Resistant and Resilient AI Paper • 2610.12233 • Published 29 days ago • 30
MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation Paper • 2609.38078 • Published Sep 29 • 37
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models Paper • 2603.28590 • Published Mar 30 • 19