Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents Paper • 2606.23085 • Published 4 days ago • 13
Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents Paper • 2606.23085 • Published 4 days ago • 13
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents Paper • 2602.22124 • Published Feb 25 • 2
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents Paper • 2502.16069 • Published Feb 22, 2025 • 20