Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing Paper • 2608.11660 • Published 5 days ago • 7
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries Paper • 2608.05604 • Published 11 days ago • 74
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 16 days ago • 252
Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents Paper • 2608.08389 • Published 8 days ago • 12
RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance Paper • 2608.09853 • Published 7 days ago • 14
From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models Paper • 2608.06020 • Published 11 days ago • 35
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 11 days ago • 46
SkillJack: Persistent Skill Backdoors in Self-Evolving Agents Paper • 2608.03509 • Published 12 days ago • 23
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published 14 days ago • 155
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents Paper • 2607.28227 • Published 18 days ago • 303