Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 6 days ago • 139
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
Steering Geometry: Validating Human Value Geometry in LLM Steering Space Paper • 2609.06289 • Published Sep 5 • 31
SPADE: Self-Play in Adaptive Synthetic Executable Environments Paper • 2608.19197 • Published Aug 19 • 56