Designing for Human-Agent Alignment: Understanding what humans want from their agents

arXiv:2404.04289v1 Announce Type: cross
Abstract: Our ability to build autonomous agents that leverage Generative AI continues to increase by the day. As builders and users of such agents it is unclear what parameters we need to align on before the agents start performing tasks on our behalf. To discover these parameters, we ran a qualitative empirical research study about designing agents that can negotiate during a fictional yet relatable task of selling a camera online. We found that for an …

abstract agent agents alignment arxiv autonomous autonomous agents build cs.ai cs.hc cs.lg designing generative human humans parameters tasks type understanding