Dr. Zero: Self-Evolving Search Agents without Training Data Paper • 2601.07055 • Published Jan 11 • 24
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents Paper • 2609.23986 • Published Sep 21 • 26
Kev Collection Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own • 6 items • Updated Oct 1 • 37
view article Article FLUX Kontext Dev Detailed Local Windows How To Tutorial — Better Than ChatGPT & Gemini Image Editing MonsterMMORPG • Jun 29, 2025 • 4
view article Article Welcome Inkling by Thinking Machines +3 burtenshaw, merve, pcuenq, ariG23498, andito • Jul 15 • 174
Agents-A1 Collection Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. • 12 items • Updated Jul 16 • 45
view article Article Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains JetBrains • Jun 1 • 40
view article Article ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM ibm-research • May 27 • 20
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding Paper • 2604.26779 • Published Apr 29 • 15
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression Paper • 2604.04921 • Published Apr 6 • 112
Synthetic Sandbox for Training Machine Learning Engineering Agents Paper • 2604.04872 • Published Apr 6 • 10