Metraipolis › archive › dc_19faa0853394

RSIGym: A Flexible Environment for Recursive Self-Improvement — arXiv:2610.10310

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10310
License (as archived)
CC0-1.0
Archived
2026-10-08T12:36:17.818Z
SHA-256 of the archived text
bc4ad2ad5c5e302aef022eaa90002ffb3382ca820e7c2dc391352540620579c6
Stable URL of this page
https://metraipolis.com/documento/dc_19faa0853394

How to cite

RSIGym: A Flexible Environment for Recursive Self-Improvement — arXiv:2610.10310 — arXiv (en), https://arxiv.org/abs/2610.10310 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19faa0853394 (Metraipolis archive dc_19faa0853394, sha256 bc4ad2ad5c5e302aef022eaa90002ffb3382ca820e7c2dc391352540620579c6)
BibTeX
@misc{dc19faa0853394,
  title = {RSIGym: A Flexible Environment for Recursive Self-Improvement — arXiv:2610.10310},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10310},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19faa0853394; sha256 bc4ad2ad5c5e302aef022eaa90002ffb3382ca820e7c2dc391352540620579c6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10310. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure. Existing settings often leave agents to rebuild routine infrastructure or restrict exploration to individual components. We introduce RSIGym, an agent-native research environment based on Everything as a Service (EaaS). RSIGym exposes training, inference, rollout, evaluation, and sandbox execution through reusable services, with shared budget and permission controls supporting Data, Harness, and Joint improvement tracks. This design enables agents to investigate individual interventions and jointly optimize data, training settings, and execution harnesses within the same environment. We define RSI-Index as the mean fraction of the remaining performance gap closed across five benchmarks covering software engineering, terminal interaction, mathematics, scientific reasoning, and skill-based tasks. Comparing six frontier research models in independent Joint runs, Opus 5 achieves the highest RSI-Index of 0.4809 under a $500 platform-service budget per benchmark run. Its selected systems improve all five benchmarks, raising SWE-bench Verified from 17.67% to 50.33% and AIME from 31.67% to 97.78%. Additional experiments examine DSH-harness refinement, budget variation, and restricted network access, while recorded trajectories reveal how agents diagnose failures and select candidates. We open-source the full RSIGym codebase and results to support reproducibility and further research.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.10310 — 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 2026-10-08T12:14:15.328Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).