AI Daybook
AI Daybook
오늘의 지면
논문Physical AI

EmbodiedEvo, 로봇 제어 코딩 에이전트가 경험을 재사용하도록 진화

EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence

매체
arXiv
게시
중요도
2/5
화제 지수
5

한국어 요약

코딩 에이전트가 프로그램을 작성하고 피드백으로 개선하는 방식으로 로봇 제어를 수행할 때, 장면마다 새로 학습하면 경험을 재사용하지 못한다는 문제를 지적했다. EmbodiedEvo는 물리적 피드백을 재사용 가능한 스킬과 교훈으로 증류하는 자체 진화 코딩 에이전트다. RoboDojo-Sim에서 평균 점수 44.48, 성공률 37.82%를 기록해 공식 검증 결과를 모두 능가했다.

원문 발췌 · English

Coding agents can construct executable programs and revise them through feedback, offering a foundation for embodied control without target-task fine-tuning. Through a programmatic robot interface, the agent observes the scene, executes control programs, and adapts them to the resulting physical state, serving as the closed-loop policy. However, this within-episode adaptation does not automatically preserve experience across scenes. Our trajectory analysis shows that agents spend interaction and inference budgets establishing effective operations and identifying their preconditions, while fresh agents cannot reuse these discoveries. This motivates EmbodiedEvo, a self-evolving coding agent that distills physical feedback into reusable code Skills and diagnostic Lessons. Experience is acquired on one Playground scene per task, then frozen for independent agents in unseen scenes, without updating model weights. On RoboDojo-Sim, EmbodiedEvo achieves an average score of 44.48 and a success rate of 37.82\%, surpassing all officially verified results. Paired tests show the largest gains on memory-dependent tasks and successful reuse of coordinated procedures, while fine contact control remains difficult. Experience from stronger models also improves weaker executors: Astra's experience raises Sol and Luna's success rates by 8.86 and 5.50 percentage points over no experience. Compared with raw interaction history, Skills and Lessons achieve comparable task performance at 53.0\% lower execution cost.

#coding-agent#robotics#embodied-ai#reinforcement-learning
원문 기사 읽기
전체 보기 →