How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings Paper • 2604.04323 • Published Apr 6 • 41
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Paper • 2602.22190 • Published Feb 25 • 17
view article Article 🚀 DTS: A Candidate for the Best Parallel Reasoning in LLMs guan-wang • Feb 11 • 14