Metraipolis › archive › dc_fcd6ca543497

RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement — arXiv:2609.35561

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35561
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:56.868Z
SHA-256 of the archived text
4598365b05013cd7fa97daa53c718efbb73b76946f0d919ce3bb8631ac9281fd
Stable URL of this page
https://metraipolis.com/documento/dc_fcd6ca543497

How to cite

RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement — arXiv:2609.35561 — arXiv (en), https://arxiv.org/abs/2609.35561 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fcd6ca543497 (Metraipolis archive dc_fcd6ca543497, sha256 4598365b05013cd7fa97daa53c718efbb73b76946f0d919ce3bb8631ac9281fd)
BibTeX
@misc{dcfcd6ca543497,
  title = {RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement — arXiv:2609.35561},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35561},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fcd6ca543497; sha256 4598365b05013cd7fa97daa53c718efbb73b76946f0d919ce3bb8631ac9281fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35561. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive self-improvement (RSI) seeks to enable AI systems to participate in improving their own capabilities. A concrete pathway is autonomous model development, where agents iteratively explore post-training strategies to improve a base model. This setting faces two challenges: agents may exploit open-ended experimental actions through hacking, and repeated experimentation may lead to strategy lock-in, where an early direction is refined rather than reconsidered. We introduce RSI-Master, which addresses the two challenges at two levels: regularize step-wise actions, avoiding hacking behaviors, and promote well-structured exploration of research directions, avoiding strategy lock-in. RSI-Master consists of an Experiment OS, which enables regularized experimental actions and maintains persistent, traceable experimental records, and Reviewer-Guided Research Orchestration, which organizes Workers and Reviewers in a dynamically growing research DAG. Workers explore diverse research directions and Reviewers compare evidence across related experiments for subsequent explorations. On PostTrainBench with Qwen3-4B-Base, it averages 54.49 versus 46.53 for the strongest agent baseline, with a 0.0\% hacking rate. Scaling to 35B model, RSI-Master surpasses the human-developed Instruct model on LiveCodeBench-v6 (41.21 vs. 37.36) and SciCode, and reaches a nonzero score on HorizonMath, a benchmark of unsolved research problems on which most frontier models score near zero.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35561 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:01.889Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).