Back to search

Article

Beyond Human-Designed Objectives: Autonomous Goal Generation in AI Through Intrinsic Motivation and Self-Directed Agency

2026-07-14

Abstract excerpt

Current artificial intelligence systems remain fundamentally constrained by their dependence on human-designed objectives and reward functions, limiting their capacity for genuine autonomy and open-ended development. This paper proposes Autonomous Goal Generation Networks (AGGNs), a theoretical framework for architectures that synthesize, evaluate, and pursue their own objectives through intrinsic motivation. The...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
de581e6e-a739-5957-b3a3-bbf52ccfe14e
DOI
10.20944/preprints202607.0905.v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Beyond Human-Designed Objectives: Autonomous Goal Generation in AI Through Intrinsic Motivation and Self-Directed AgencyDOI 10.20944/preprints202607.0905.v1
Select a neighboring publication to make it the new centre.