CoLA: Multi-VLA Coordination via Learned Adapters
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
Vision-Language-Action (VLA) models are typically deployed as isolated single-agent policies. When several such agents share a workspace, they can coordinate implicitly, by observing one another, or explicitly, by exchanging messages, but it remains unclear when explicit communication becomes necessary.
초록에서 가져왔습니다. 요약을 준비 중입니다.