📚 Also Explained

• Reward-Weighted Preference Optimization for Selective Com... 2610.31239
• Mixture-of-Recursions: Learning Dynamic Recursive Depths ... 2507.10524
• Evolving Agent Interfaces 2610.28601
• Beyond Behavioral Accuracy: Evaluating Individual-Level F... 2610.26524
• StebBench: Diagnosing Real-World Procedural Understanding... 2610.26679
• Honeypots for AI Agent Insider Threats 2610.26664
• When the harness decides success: state that cannot be re... 2610.26632
• Is Sycophancy a Form of In-Context Updating? 2610.28325
• DIVE: Benchmarking Full-Duplex Interaction with Visual En... 2610.28405
• BetaMem: Learning to Remember a Changing World for Embodi... 2610.26554