Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine

ICLROral2026

Authors: Wenyi Wang, Piotr Piękos, Li Nanbo, Firas Laakom, Yimeng Chen, Mateusz Ostaszewski, Mingchen Zhuge, Jürgen Schmidhuber
Affiliation: King Abdullah University of Science and Technology
Venue: ICLR 2026
Track: Oral

TL;DR

We propose Huxley-G\"odel Machine, an algorithm guideing self-improvements following an estimation of the value function of G\"odel Machines.

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

agent

← All ICLR 2026 Oral papers · Browse the whole archive