Researcher Lets Codex Run the Experiments, Publishes Recurrent Model Length-Extrapolation Paper

qixing_huang · x · 2026-09-10

Hanwen Jiang describes a highly automated research collaboration with Codex: the agent proposed hypotheses, implemented and debugged methods, ran experiments and iterated, while he set direction and judged evidence. He argues the workflow shines when problems are near-pure logic with cheap verification. The result is a paper, Learning Length-Extrapolatable Recurrent Models (arXiv:2609.09157), which traces long-context failures to state credit and proposes Credit Stabilization through Time (CST), improving performance up to 128x the training horizon.

Original post →

More from coding & agent

coding & agent channel →