Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps Paper • 2610.02740 • Published Oct 2 • 7
Evaluating LLM Creativity through Long-Tail Performance Paper • 2610.12998 • Published 26 days ago • 11
Scaling Agentic Data for Long-Horizon Terminal Intelligence Paper • 2610.13166 • Published 26 days ago • 129
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 27 days ago • 138
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents Paper • 2610.18614 • Published 22 days ago • 6
AutoEnvScaling: Automating the Data Flywheel with Terminal Agents Paper • 2610.14163 • Published 26 days ago • 13
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes Paper • 2610.18356 • Published 22 days ago • 118
Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching Paper • 2610.19636 • Published 21 days ago • 8
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models Paper • 2610.22428 • Published 20 days ago • 12
OfficeTown: Generative Organizations for Evolving Agent Intelligence Paper • 2610.23194 • Published 19 days ago • 22
S-Agent 2.0: Spatial Reasoning with a General Coding Agent Paper • 2610.28354 • Published 15 days ago • 40
Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents Paper • 2610.11942 • Published 27 days ago • 9
DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model Paper • 2610.31734 • Published 13 days ago • 20
Building Auditable AI Text Detectors with Sparse Autoencoders Paper • 2610.30006 • Published 14 days ago • 14
meta-models/Muse-Spark-Open-816B-A42B Image-Text-to-Text • 822B • Updated 20 days ago • 10.4k • • 738