Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills Paper • 2603.25158 • Published 5 days ago • 33
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens Paper • 2603.23516 • Published 25 days ago • 39
Qworld: Question-Specific Evaluation Criteria for LLMs Paper • 2603.23522 • Published 24 days ago • 9
OpenResearcher Collection OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis • 8 items • Updated 7 days ago • 14
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents Paper • 2603.22386 • Published 7 days ago • 54
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning Paper • 2603.23483 • Published 6 days ago • 58
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search Paper • 2603.22341 • Published 10 days ago • 35
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 13 days ago • 91
In-Context Reinforcement Learning for Tool Use in Large Language Models Paper • 2603.08068 • Published 22 days ago • 42
view article Article Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI 13 days ago • 58
view article Article From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels Aug 18, 2025 • 95
Mamba-3: Improved Sequence Modeling using State Space Principles Paper • 2603.15569 • Published 14 days ago • 6
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation Paper • 2603.08652 • Published 21 days ago • 39