Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps Paper • 2610.02740 • Published Oct 2 • 7
Scaling Agentic Data for Long-Horizon Terminal Intelligence Paper • 2610.13166 • Published Oct 9 • 128
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents Paper • 2610.18614 • Published Oct 13 • 7
AutoEnvScaling: Automating the Data Flywheel with Terminal Agents Paper • 2610.14163 • Published Oct 9 • 14
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes Paper • 2610.18356 • Published Oct 13 • 119
Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching Paper • 2610.19636 • Published Oct 14 • 8
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models Paper • 2610.22428 • Published Oct 15 • 11
OfficeTown: Generative Organizations for Evolving Agent Intelligence Paper • 2610.23194 • Published Oct 16 • 22
S-Agent 2.0: Spatial Reasoning with a General Coding Agent Paper • 2610.28354 • Published 27 days ago • 39
Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents Paper • 2610.11942 • Published Oct 8 • 9
DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model Paper • 2610.31734 • Published 25 days ago • 20
Building Auditable AI Text Detectors with Sparse Autoencoders Paper • 2610.30006 • Published 26 days ago • 14