---
id: 20260924-T0-14
title: "AIBuildAI-2.5：用LLM引导的树搜索自动构建AI模型"
title_en: "AIBuildAI-2.5 Uses LLM-Guided Tree Search to Build AI Models Autonomously"
url: https://ai.daily.yangsir.net/daily/20260924-T0-14
issue_date: 2026-09-24
publish_date: 2026-09-23T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2609.25047
---

# AIBuildAI-2.5：用LLM引导的树搜索自动构建AI模型

arXiv论文提出AIBuildAI-2.5，一种通过LLM引导树搜索自动构建AI模型的智能体方案。该方法将模型构建建模为代码搜索问题，用树搜索求解，让自主智能体自动完成AI模型开发，降低科研和工程领域的AI使用门槛。论文编号arXiv:2609.25047v1，属cs.CL方向。

## English Version

**AIBuildAI-2.5 Uses LLM-Guided Tree Search to Build AI Models Autonomously**

A new arXiv paper introduces AIBuildAI-2.5, an autonomous agent that builds AI models via LLM-guided tree search. The approach frames model building as a code search problem solved by tree search, enabling agents to automatically develop AI models and broadening access to AI across science and engineering. Paper ID: arXiv:2609.25047v1, under cs.CL.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2609.25047)

**详情页**：https://ai.daily.yangsir.net/daily/20260924-T0-14

---

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