Researcher: any agent acting over long horizons provably has a self-model and world model

chris_j_paxton · x · 2026-09-16

In reply to Chris Paxton, researcher Aran Nayebi sketches a theorem-style argument: an agent that can act over long horizons can be proven to internally model an action-conditioned world model — meaning it models the consequences of its own actions and therefore must have some model of itself.

This offers a formalizable angle on the debate over whether LLM-based agents have internal world models or self-representations: a self-model doesn't imply consciousness, but long-horizon agency mathematically entails an internal representation of one's own action consequences. Link to paper details included.

Original post →

More from AGI Musings

AGI Musings channel →