Hierarchical planning allows AI systems to decompose complex goals into multiple levels of abstraction: high-level planning works with macro actions and abstract representations over longer timescales (e.g., 'go to the airport'), while lower levels plan detailed actions over shorter timescales (e.g., 'walk to the elevator, push button, descend')—humans do hierarchical planning constantly, but learning machines have almost no capability to do this; nearly all robots use hand-crafted representations at each hierarchy level rather than learned abstractions.

factualpending

Speaker

Yann LeCun

Evidence Quote

“we do hierarchical planning absolutely all the time...we have no idea how to do this with learning machines”

Source

The Shape of AI to Come! Yann LeCun at AI Action Summit 2025— DSAI by Dr. Osbert Tay
Created: 8/11/2026, 1:17:36 AM

Your notes

Loading notes...