---
id: 20261114-T0-08
title: "AutoAssumption：搜索隐含假设可自动发现ML系统算法"
title_en: "AutoAssumption: Searching Over Assumptions Discovers ML-Systems Algorithms"
url: https://ai.daily.yangsir.net/daily/20261114-T0-08
issue_date: 2026-11-14
publish_date: 2026-11-13T05:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2611.14844
---

# AutoAssumption：搜索隐含假设可自动发现ML系统算法

研究者提出AutoAssumption，通过系统性搜索隐含假设来自动发现ML系统算法。许多ML系统进展源于打破前人默认的假设，例如投机解码放弃了每个token需要一次前向传播的假设，但算法很少明确写出自己的假设。AutoAssumption将假设显式化并搜索替代方案，从而自动找到新的算法设计。该方法为ML系统优化提供了可自动化的算法发现路径。

## English Version

**AutoAssumption: Searching Over Assumptions Discovers ML-Systems Algorithms**

Researchers proposed AutoAssumption, which automatically discovers ML-systems algorithms by systematically searching over implicit assumptions. Many advances in ML systems came from breaking assumptions earlier methods took for granted, such as speculative decoding dropping the one-forward-pass-per-token assumption, yet algorithms rarely state their assumptions. AutoAssumption makes assumptions explicit and searches alternatives to find new algorithm designs automatically, offering an automatable path for ML systems optimization.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2611.14844)

**详情页**：https://ai.daily.yangsir.net/daily/20261114-T0-08

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*