Nov. 5, 2023, 6:42 a.m. | Hussein Mozannar, Jimin J Lee, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag

cs.LG updates on arXiv.org arxiv.org

People are relying on AI agents to assist them with various tasks. The human
must know when to rely on the agent, collaborate with the agent, or ignore its
suggestions. In this work, we propose to learn rules grounded in data regions
and described in natural language that illustrate how the human should
collaborate with the AI. Our novel region discovery algorithm finds local
regions in the data as neighborhoods in an embedding space that corrects the
human prior. Each …

agent agents ai agents arxiv data human language learn natural natural language onboarding people rules suggestions tasks teams them work

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote