Qworld: Question-Specific Evaluation Criteria for LLMs Paper • 2603.23522 • Published 22 days ago • 9
OpenResearcher Collection OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis • 8 items • Updated 4 days ago • 14
CohereLabs/cohere-transcribe-03-2026 Automatic Speech Recognition • Updated about 12 hours ago • 12.1k • 309
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents Paper • 2603.22386 • Published 5 days ago • 51
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning Paper • 2603.23483 • Published 4 days ago • 57
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search Paper • 2603.22341 • Published 7 days ago • 33
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 11 days ago • 88