Metraipolis › archive › dc_e2b4b0ce269e
AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search — arXiv:2609.25047
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25047
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:45:57.534Z
- SHA-256 of the archived text
327f70f46902afdb2c29ae171de1ed85f8579012da09f89ef6fc91a6532943c1- Stable URL of this page
https://metraipolis.com/documento/dc_e2b4b0ce269e
How to cite
AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search — arXiv:2609.25047 — arXiv (en), https://arxiv.org/abs/2609.25047 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2b4b0ce269e (Metraipolis archive dc_e2b4b0ce269e, sha256 327f70f46902afdb2c29ae171de1ed85f8579012da09f89ef6fc91a6532943c1)
BibTeX
@misc{dce2b4b0ce269e,
title = {AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search — arXiv:2609.25047},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25047},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2b4b0ce269e; sha256 327f70f46902afdb2c29ae171de1ed85f8579012da09f89ef6fc91a6532943c1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25047. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line of such agents frames model building as a code search problem and solves it by tree search, in which each node is a candidate program and the tree grows by generating a child program from a parent, and these agents now approach the capability of experienced AI engineers on realistic benchmarks. However, these agents have three weaknesses in efficiency that have not been fully addressed. First, only a small number of candidates can be executed within a realistic budget, so search rules that rank nodes by executed rewards, such as Monte Carlo-style tree search, rely on few and noisy scores and select the next node to explore less effectively. Second, no resource-aware strategy is used to schedule training jobs, which can lower hardware utilization and training efficiency. Third, every agent call is served by a single powerful model, which inflates inference cost. Here we introduce AIBuildAI-2.5, an agentic system that carries out the tree search with LLM agents and addresses each of the three issues. AIBuildAI-2.5 proposes a novel LLM-guided tree search, in which a judge scores each candidate on its expected improvement, grounding, and feasibility, and a selector ranks the pool of candidates from these scores and the state of the search. In addition, AIBuildAI-2.5 comprises a scheduler that launches training jobs with the current hardware resource status taken into account and a router that assigns lower-cost LLMs to less demanding tasks while reserving the most capable LLM for the most challenging sub-tasks in the AI model building workflow. AIBuildAI-2.5 ranks first on MLE-Bench with a medal rate of 73.3%, and outperforms a strong baseline on six autonomous AI research tasks from AIRS-Bench. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.25047 — 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 2026-10-08T13:18:38.187Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).