False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 151
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published Sep 27 • 101
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published Sep 28 • 89
VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models Paper • 2609.32607 • Published Sep 26 • 42