Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations Paper • 2504.13816 • Published 20 days ago • 17
FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving Paper • 2502.20238 • Published Feb 27 • 24
Open-Reasoner-Zero/Open-Reasoner-Zero-7B Reinforcement Learning • Updated about 1 month ago • 1.01k • 28
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis Paper • 2412.19723 • Published Dec 27, 2024 • 88