Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents Paper β’ 2611.17167 β’ Published 6 days ago β’ 39
Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference Paper β’ 2611.10193 β’ Published 12 days ago β’ 18
WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models Paper β’ 2603.27343 β’ Published 19 days ago β’ 9
World In-Context Learning for Agentic Robot Manipulation Paper β’ 2611.12885 β’ Published 9 days ago β’ 59
Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand Paper β’ 2611.00883 β’ Published 18 days ago β’ 54
GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling Paper β’ 2610.37257 β’ Published 18 days ago β’ 38
SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding? Paper β’ 2611.06083 β’ Published 14 days ago β’ 7
SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding Paper β’ 2611.02501 β’ Published 16 days ago β’ 21
Sleeping Agents 4 Radiology Report Generation in Indic Languages π¬ 4 Generate chest Xβray reports and translate them to Indic languages
Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute? Paper β’ 2610.39497 β’ Published 20 days ago β’ 74
RoboHarness: A Simple Harness Outperforms VLA and World Action Models Paper β’ 2610.14018 β’ Published Oct 16 β’ 7