Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation Paper • 2610.02788 • Published 4 days ago • 15
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution Paper • 2610.03675 • Published 4 days ago • 21
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It Paper • 2610.03195 • Published 4 days ago • 37
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 5 days ago • 260
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published 4 days ago • 53
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 10 days ago • 323
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation Paper • 2609.36601 • Published 7 days ago • 94
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 9 days ago • 564