A coding agent turns one trial into reusable skills: EmbodiedEvo scores 44.48 average on RoboDojo simulation
EmbodiedEvo lets a coding agent revise code through physical feedback on a single Playground scene, freeze the successful control procedures and failure conditions as reusable Skills and Lessons, and hand them to independent agents on new scenes. On RoboDojo-Sim, the Astra/xhigh configuration reaches 44.48 average score and 37.82% success rate, above all officially verified leaderboard results; in paired tests with task description alone, success rises from 8.50% to 30.17%, with gains concentrated on memory-dependent tasks while fine contact control remains difficult.