SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries Paper • 2608.05604 • Published 8 days ago • 72
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 13 days ago • 159
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents Paper • 2608.08814 • Published 5 days ago • 10
EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal Paper • 2608.05565 • Published 8 days ago • 22
On-Policy Delta Distillation for Multilingual Math Reasoning Paper • 2608.05802 • Published 8 days ago • 32
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Paper • 2608.05102 • Published 9 days ago • 65
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 11 days ago • 155
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering Paper • 2607.28568 • Published 15 days ago • 183