Metraipolis › archive › dc_aa9dcec791cd
Infinity Machine: a self-improving AI agent for research — arXiv:2610.35579
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35579
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:58:39.691Z
- SHA-256 of the archived text
e36c7500af549eadcd7b172a8532468f49a345498a47183c0f1fab763c510fe1- Stable URL of this page
https://metraipolis.com/documento/dc_aa9dcec791cd
How to cite
Infinity Machine: a self-improving AI agent for research — arXiv:2610.35579 — arXiv (en), https://arxiv.org/abs/2610.35579 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa9dcec791cd (Metraipolis archive dc_aa9dcec791cd, sha256 e36c7500af549eadcd7b172a8532468f49a345498a47183c0f1fab763c510fe1)
BibTeX
@misc{dcaa9dcec791cd,
title = {Infinity Machine: a self-improving AI agent for research — arXiv:2610.35579},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35579},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa9dcec791cd; sha256 e36c7500af549eadcd7b172a8532468f49a345498a47183c0f1fab763c510fe1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35579. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present the Infinity Machine, a self-improving AI agent that we use for research on problems whose answers aprogram or data can check. Each candidate solution is produced by a full tool-using agent that works for up to an hour in a fresh sandbox; proposers see only a public score, and a private split decides what counts. The harness itself(prompts, tools, skills, playbook, meta agent) is an editable genome, changed only through a kernel-enforced gate with held-out and cost checks. An autonomous mode goes from a plain-text goal to a verified report with no human step: an agent picks an open problem and writes its verifier, the kernel calibrates it, an adversarial agent audits it, and an agent that never sees the verifier re-checks the result. Across fourteen problems in six days, for about $180 of model usage, the system produced four results beyond the published state of the art on catalogued open problems in quantum information: a certified depolarizing-channel threshold point p = 0.064966, a qutrit positivity frontier of 0.2910672, a 44-gate depth-6 Golay state preparation, and a stabilizer-rank bound chi(T^7) <= 10. It also cut SABRE qubit-routing overhead from 68,559 to 12,087 added gates. In hardware, it cut the energy per MAC of an open 8x8 INT8 systolic tile by 77.7% through a full open RTL-to-GDS flow, bit-exact. Three fully autonomous runs ended in honestties with public records; one audit caught a stale record, and one agent-written score pointing the wrong way went unnoticed. We report the failures as carefully: the one self-derived harness generation was rejected on cost, proposers gamed lenient scorers four times, and operator changes were decisive for several results. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.35579 — 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 2026-10-27T07:55:30.760Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).