Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation Paper • 2610.02788 • Published 9 days ago • 18
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution Paper • 2610.03675 • Published 9 days ago • 29
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It Paper • 2610.03195 • Published 9 days ago • 46
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 10 days ago • 279
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published 9 days ago • 60
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 15 days ago • 326
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation Paper • 2609.36601 • Published 12 days ago • 95
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 14 days ago • 674