SPEAR: חמש עקרונות להתאמה אינטראקטיבית של בני אדם ואגנטים

תקציר מקורי באנגליתarXiv:2610.07204v1 Announce Type: cross Abstract: Recent AI alignment work often frames alignment as a pre-deployment optimization problem: collect human feedback, learn preferences or principles, finetune the model, and deploy an aligned system. This framing has produced major progress, but it under-specifies what happens once AI systems act as agents on users' behalf in situated, long-term, and social contexts. This position paper reframes human-agent alignment as an ongoing interaction design problem. We propose SPEAR, five pillars of interactive alignment: Specification (how people express intent and establish shared understanding), Process (how agents decide when to act, ask, defer, or pause), Evaluation (how people judge whether agents succeeded), Adaptation (how agents adapt to user