GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks Paper • 2608.03764 • Published 4 days ago • 23
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 5 days ago • 152
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction Paper • 2607.29677 • Published 8 days ago • 23