Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub Paper • 2610.11169 • Published 6 days ago • 5
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Paper • 2609.19499 • Published 28 days ago • 37
Agora: Git as Shared Memory for Collective AutoResearch Paper • 2609.18094 • Published 28 days ago • 59
MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes Paper • 2609.10016 • Published Sep 9 • 29
Agentic Visual Generation: From Generative Models to Agentic Control Paper • 2609.06758 • Published Sep 6 • 34