RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published Oct 1 • 167
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement Paper • 2603.06333 • Published Mar 6 • 2
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops Paper • 2607.07663 • Published Jul 8 • 3