Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning Paper • 2505.16410 • Published 12 days ago • 55
NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification Paper • 2505.16938 • Published 12 days ago • 113
Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits Paper • 2505.14648 • Published 14 days ago • 8