EmbodiedSWE, coding agents for dexterous robotics, wins Best Paper at CoRL 2026 workshop
shahdhruv_ · x · 2026-11-13
EmbodiedSWE, which applies frontier coding agents to long-horizon dexterous robotics, won the Best Paper Award at the CoRL 2026 Workshop on Agentic Robotics. The project has four parts: EmbodiedSWE-Bench (6 suites, 28 everyday dexterous tasks, 17 embodiments — lightbulb screwing, IKEA assembly, latte art, food cutting, warehouse picking); large-scale evaluation of frontier agents on completion, time, and inference cost; EmbodiedSWE-Gen, which diversifies verified solutions into large trajectory datasets for training a general robot policy; and seed-task generation with RL to improve the coding agent itself. Advisors include Katerina Fragkiadaki and Peter Henderson.
Related event: EmbodiedSWE wins Best Paper at CoRL 2026 Agentic Robotics Workshop(2 posts)→
More from Embodied
- Stanford's autonomous robotics textbook and course materials now free online — StanfordHAI · 2026-11-14
- Russ Tedrake's CoRL talk: coupling deployment data with large-scale pretraining — RussTedrake · 2026-11-14
- X-Era AI Lab's world-action model hits 85-88% robot manipulation success rates — jiqizhixin · 2026-11-14
- Figure AI seen most exposed to Nvidia fallout: $3.5-6B compute deal in limbo — kscottz · 2026-11-14
- 5,400 real-robot rollouts benchmark Claude Fable 5.2 at 65%, ahead of Gemini and GPT — ricklamers · 2026-11-14
- EmbodiedSWE wins CoRL 2026 Best Paper: coding agents generate robot training data — PeterHndrsn · 2026-11-14