arXiv cs.CL· Jimmy Lin, Sahel Sharifymoghaddam, Lingwei Gu, Nour Jedidi·· 9 天前AI 评分33
Project Greenhouse：迈向完全开放与自主的智能体搜索
Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search
AI 导读
Project Greenhouse 探索仅用少量 GPU 从零预训练加监督微调，构建完全开放、自主可控的智能体搜索模型，不依赖第三方开源权重骨干。团队发布 Gaggle 系列模型 checkpoint 及数据、代码与配置，支持训练全流程的透明独立复现。
正文 · 原文
Abstract:Project Greenhouse represents our exploration of a simple thesis: We believe that it is possible to build fully open and sovereign models for agentic search with only modest computational resources. As a first milestone, we describe how to build a competitive pointwise decoder-only reranker using a simple two-step recipe comprising pre-training from scratch followed by supervised fine-tuning, starting only from commonly available datasets. Contrary to the dominant approach in the literature, we do not rely on existing open-weight backbones from third parties, and thus we are fully in control of model training, from end to end. We were able to accomplish the bulk of our experiments using no more than a handful of GPUs. This report articulates the importance and benefits of our approach, and we share artifacts that enable transparent, independent reproduction of all aspects of model training. Beyond data, code, and configurations that capture our efforts, we also release checkpoints for our family of Gaggle models, demonstrating the feasibility of our approach and providing a first step toward validating our broader thesis.
| Subjects: | Information Retrieval (cs.IR); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.11922 [cs.IR] |
| (or arXiv:2610.11922v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11922 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jimmy Lin [view email]
[v1]
Thu, 8 Oct 2026 13:19:46 UTC (87 KB)
来源：arXiv cs.CL · arxiv.org