The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 3 days ago • 539
EnvLunch: The Environment as a Free Lunch for Learning to Interact Paper • 2610.33817 • Published 5 days ago • 6
TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models Paper • 2610.25376 • Published 11 days ago • 14
SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving Paper • 2610.20609 • Published 15 days ago • 16
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published 21 days ago • 63
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction Paper • 2609.10715 • Published Sep 9 • 205