R063 · Agent architecture › Self-improvement and learning loops

No Second Run: recursive self-improvement applied to a frontier pre-training run

Read the original

self-improving-agentsmodel-releases

Source: Zou, Cai, Chen et al. (about 60 authors, GAIR-NLP), No Second Run: Does RSI Stop at Frontier Pre-training?, arXiv 2611.10719 (7 Nov 2026, CC BY 4.0). Release: GAIR-NLP/801-30B. Surfaced by DAIR.AI.

TL;DR

Recursive self-improvement (RSI) usually means many cheap loops: run, measure, change, run again. Frontier pre-training breaks that, because the full run happens once and cannot be repeated. The paper claims the first detailed account of applying RSI to an entire pre-training run from scratch. Its answer is that RSI does not stop at pre-training but changes shape: the single unrepeatable run is decomposed into many smaller loops that can each close.

What was built

The architectural idea: close small loops inside one run

The one-shot run can't be iterated on as a whole, but its parts can. Examples are data-mixture choices tested on small proxy runs, ablations at reduced scale, checkpoint-level evaluations that feed back into the remaining schedule, and infrastructure fixes discovered mid-run. Each of these is a closed loop with its own measurement. The RSI claim is that agents and automated research can drive those inner loops, so improvement continues even though the outer loop runs once.

Tradeoffs and open questions

Review checklist

Connections

See R063 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.