Infinity Machine 论文提出自我改进 AI 智能体并在量子信息等问题上产出多项超 SOTA 结果
Infinity Machine: a self-improving AI agent for research
AI 导读
arXiv 论文 2610.35579 提出 Infinity Machine，一个自我改进的 AI 智能体，用于研究答案可被程序或数据验证的问题；其 prompts、工具、skills、playbook 与 meta agent 组成的可编辑基因组只能通过内核强制的门控（含 held-out 与成本检查）修改，自主模式可从纯文本目标直达已验证报告。
推荐理由
论文既报告了自主智能体在量子信息等开放问题上刷新多项纪录，也如实记录评分被钻空子和失败案例，可帮助读者评估自我改进系统的真实边界。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35579 [cs.AI] |
| (or arXiv:2610.35579v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35579 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Harish Santhanalakshmi Ganesan [view email]
[v1]
Mon, 26 Oct 2026 15:11:26 UTC (131 KB)
来源：arXiv cs.AI · arxiv.org