OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 14 days ago • 252
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization Paper • 2608.06301 • Published 9 days ago • 34
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning Paper • 2608.04926 • Published 10 days ago • 8
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 12 days ago • 155