From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents Paper • 2603.22386 • Published 3 days ago • 47
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning Paper • 2603.23483 • Published 2 days ago • 50
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search Paper • 2603.22341 • Published 5 days ago • 29
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 9 days ago • 78
In-Context Reinforcement Learning for Tool Use in Large Language Models Paper • 2603.08068 • Published 17 days ago • 41
view article Article Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI 9 days ago • 54
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 10 days ago • 6
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation Paper • 2603.08652 • Published 17 days ago • 39
LLM2Vec-Gen: Generative Embeddings from Large Language Models Paper • 2603.10913 • Published 15 days ago • 43
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse Paper • 2603.12201 • Published 14 days ago • 52
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning Paper • 2603.00889 • Published 26 days ago • 55