Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning Paper • 2505.24726 • Published 7 days ago • 165
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning Paper • 2503.07572 • Published Mar 10 • 46
view article Article CodeAgents + Structure: A Better Way to Execute Actions By akseljoonas and 1 other • 10 days ago • 43
view article Article Interactive Tools for machine learning, deep learning, and math By Suzana • 11 days ago • 40
view article Article Tiny Agents in Python: a MCP-powered agent in ~70 lines of code By celinah and 3 others • 15 days ago • 122
view article Article Microsoft and Hugging Face expand collaboration By jeffboudier and 2 others • 19 days ago • 20
view article Article TinyAgents: A Minimal Experiment with Code Agents and MCP Tools By albertvillanova • 22 days ago • 29
view article Article Vision Language Models (Better, Faster, Stronger) By merve and 4 others • 26 days ago • 417
view article Article Reduce, Reuse, Recycle: Why Open Source is a Win for Sustainability By sasha and 1 other • about 1 month ago • 14
view article Article What is MoE 2.0? Update Your Knowledge about Mixture-of-experts By Kseniase and 1 other • Apr 27 • 9
view article Article 20 Awesome MCP Servers List I Have Collected (You Should Try Too) By lynn-mikami • Mar 25 • 8
view article Article Consent by Design: Approaches to User Data in Open AI Ecosystems By giadap and 1 other • Apr 17 • 13