Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 5 days ago • 520
Demystifying Agent Skills: Why They Work-Until They Don't Paper • 2608.14036 • Published 24 days ago • 169
Recursive Synthesis for Long-Horizon Terminal Tasks Paper • 2608.05466 • Published about 1 month ago • 252
Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs Paper • 2608.01755 • Published Aug 3 • 142
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations Paper • 2607.19865 • Published Jul 22 • 9
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists Paper • 2607.11079 • Published Jul 13 • 10
PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection Paper • 2607.04690 • Published Jul 6 • 3
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published Jun 15 • 178
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models Paper • 2606.11324 • Published Jun 9 • 173
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published Jun 11 • 114