{"slug": "aibuildai-2-5-efficient-autonomous-ai-model-development-through-llm-guided-tree", "title": "AIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search", "summary": "AIBuildAI-2.5, an agentic system that uses LLM-guided tree search to automate AI model development, ranked first on MLE-Bench with a medal rate of 73.3%, according to the arXiv paper 2609.25047v1. The system adds a judge that scores candidates on expected improvement, grounding, and feasibility, a hardware-aware scheduler for training jobs, and a router that assigns lower-cost LLMs to less demanding tasks while reserving the most capable LLM for the hardest sub-tasks. AIBuildAI-2.5 also outperformed a strong baseline on six autonomous AI research tasks from AIRS-Bench.", "body_md": "arXiv:2609.25047v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/aibuildai-2-5-efficient-autonomous-ai-model-development-through-llm-guided-tree", "canonical_source": "https://arxiv.org/abs/2609.25047", "published_at": "2026-09-23 04:00:00+00:00", "updated_at": "2026-09-23 04:25:24.247732+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models", "machine-learning"], "entities": ["AIBuildAI-2.5", "MLE-Bench", "AIRS-Bench", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/aibuildai-2-5-efficient-autonomous-ai-model-development-through-llm-guided-tree", "markdown": "https://wpnews.pro/news/aibuildai-2-5-efficient-autonomous-ai-model-development-through-llm-guided-tree.md", "text": "https://wpnews.pro/news/aibuildai-2-5-efficient-autonomous-ai-model-development-through-llm-guided-tree.txt", "jsonld": "https://wpnews.pro/news/aibuildai-2-5-efficient-autonomous-ai-model-development-through-llm-guided-tree.jsonld"}}