Metraipolis › archive › dc_05d09209296a
Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search — arXiv:2610.11922
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11922
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:13:50.219Z
- SHA-256 of the archived text
a997ca070f6925255b3e05905daab604b383f03cd187c4c235af5d4bbe356a93- Stable URL of this page
https://metraipolis.com/documento/dc_05d09209296a
How to cite
Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search — arXiv:2610.11922 — arXiv (en), https://arxiv.org/abs/2610.11922 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_05d09209296a (Metraipolis archive dc_05d09209296a, sha256 a997ca070f6925255b3e05905daab604b383f03cd187c4c235af5d4bbe356a93)
BibTeX
@misc{dc05d09209296a,
title = {Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search — arXiv:2610.11922},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11922},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_05d09209296a; sha256 a997ca070f6925255b3e05905daab604b383f03cd187c4c235af5d4bbe356a93},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11922. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.11922 — 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 2026-10-09T05:47:15.504Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).