ASI-LIB-018 technical code available

Huxley-Godel Machine: Human-Level Coding Agent Development

Wenyi Wang, Piotr Piekos, Li Nanbo, Firas Laakom, Yimeng Chen, Mateusz Ostaszewski, Mingchen Zhuge, Juergen Schmidhuber

Huxley-Godel Machine agent illustration
Figure via ar5iv rendering of arXiv:2510.21614

HGM sharpens an important point: an agent that scores best now is not necessarily the agent with the best descendants. The paper calls this a metaproductivity-performance mismatch.

Technical move

The proposed CMP metric aggregates descendant performance as a proxy for an agent’s self-improvement potential. Search is then guided toward lineages that are productive, not only toward nodes that look best under the current benchmark.

ASI relevance

Recursive improvement is a lineage problem. If the objective only selects for near-term benchmark wins, the search may discard systems that would have become better improvers after a few generations.