AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models

• URL: http://arxiv.org/abs/2605.27873v1
• Date: Wed, 27 May 2026 02:44:13 GMT
• Title: AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models
• Abstract summary: AI models underpin data-centric applications from image and text processing to scientific discovery in biology, physics, and chemistry.<n>Yet developing them remains heavily manual, requiring practitioners to design architectures, build training pipelines, and iteratively refine solutions.<n>We introduce AIBuildAI-2, a knowledge-enhanced agent with an external, evolving knowledge system for automatically building AI models.
• Score: 31.05147308924019
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: AI models underpin data-centric applications from image and text processing to scientific discovery in biology, physics, and chemistry. Yet developing them remains heavily manual, requiring practitioners to design architectures, build training pipelines, and iteratively refine solutions, making it challenging for natural scientists without specialized AI engineering expertise to build the high-performing models their research demands. To reduce this burden and broaden access to AI for scientific discovery, agents that automatically build AI models have been proposed. However, the performance of these agents is largely limited by the parametric knowledge of their underlying large language models, which is static, often outdated, and sparse on practical AI model engineering know-how. To address this limitation, we introduce AIBuildAI-2, a knowledge-enhanced agent with an external, evolving knowledge system for automatically building AI models. The knowledge system of AIBuildAI-2 is hierarchical, organizing curated AI development knowledge into high-level knowledge instructions over topical categories and low-level knowledge documents under each category, from which the agent dynamically loads only the context relevant to its current state and the AI task being solved, grounding each design and implementation decision in concrete, externally verifiable expertise. The system is initialized by collecting and cleaning AI-development-related documents from the web and organizing them into the corresponding categories, and continually evolves from the agent's own experience by distilling each completed run on an AI task into structured takeaways that are written back into the knowledge system. AIBuildAI-2 achieves state-of-the-art results, ranking first on MLE-Bench with a 70.7% medal rate and placing in the top 6.6% among 4,370 human-expert teams in a heart disease prediction competition.

Related papers

• Toward Reusability of AI Models Using Dynamic Updates of AI Documentation [1.503974529275767]
  This work addresses the challenge of disseminating reusable artificial intelligence (AI) models accompanied by AI documentation (a.k.a., AI model cards)<n>Our objectives are to shorten the lag time in updating AI model card templates and align AI documentation more closely with current AI best practices.<n>The impact of our work lies in introducing a methodology for delivering agile, data-driven, and community-based standards for documenting AI models and improving AI model reuse.
  arXiv  Detail & Related papers  (2026-04-19T21:42:37Z)
• AIBuildAI: An AI Agent for Automatically Building AI Models [31.05147308924019]
  We introduce AIBuildAI, an AI agent that automatically builds AI models from a task description and training data.<n>We evaluate AIBuildAI on MLE-Bench, a benchmark of realistic Kaggle-style AI development tasks.
  arXiv  Detail & Related papers  (2026-04-15T22:17:05Z)
• AI Co-Scientist for Ranking: Discovering Novel Search Ranking Models alongside LLM-based AI Agents with Cloud Computing Access [60.37646376282544]
  We present an AI Co-Scientist framework that automates the full search ranking research pipeline.<n>This is the first study in the ranking community to utilize an AI Co-Scientist framework for algorithmic research.
  arXiv  Detail & Related papers  (2026-03-23T09:29:08Z)
• Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery [81.03797680309154]
  DBench-Bio is a dynamic and fully automated benchmark to evaluate AI's biological knowledge discovery ability.<n>We instantiate this pipeline to construct a monthly-updated benchmark covering 12 biomedical sub-domains.<n>Our work provides the first dynamic, automatic framework for assessing the new knowledge discovery capabilities of AI systems.
  arXiv  Detail & Related papers  (2026-02-10T05:47:22Z)
• Report for NSF Workshop on AI for Electronic Design Automation [56.48556959103223]
  This report distills the discussions and recommendations from the NSF Workshop on AI for Electronic Design Automation (EDA)<n>Bringing together experts across machine learning and EDA, the workshop examined how AI-spanning large language models (LLMs), graph neural networks (GNNs), reinforcement learning (RL), neurosymbolic methods, etc.<n>The report recommends NSF to foster AI/EDA collaboration, invest in foundational AI for EDA, develop robust data infrastructures, promote scalable compute infrastructure, and invest in workforce development to democratize hardware design and enable next-generation hardware systems.
  arXiv  Detail & Related papers  (2026-01-20T23:45:40Z)
• Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training [67.895981259683]
  General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence.<n>Current agent systems are either closed-source or heavily reliant on a variety of paid APIs and proprietary tools.<n>We present Cognitive Kernel-Pro, a fully open-source and (to the maximum extent) free multi-module agent framework.
  arXiv  Detail & Related papers  (2025-08-01T08:11:31Z)
• General Scales Unlock AI Evaluation with Explanatory and Predictive Power [57.7995945974989]
  benchmarking has guided progress in AI, but it has offered limited explanatory and predictive power for general-purpose AI systems.<n>We introduce general scales for AI evaluation that can explain what common AI benchmarks really measure.<n>Our fully-automated methodology builds on 18 newly-crafted rubrics that place instance demands on general scales that do not saturate.
  arXiv  Detail & Related papers  (2025-03-09T01:13:56Z)
• Compliance Cards: Automated EU AI Act Compliance Analyses amidst a Complex AI Supply Chain [9.991293429067065]
  We introduce a complete system for provider-side AIA compliance analyses amidst a complex AI supply chain. First is an interlocking set of computational, multi-stakeholder transparency artifacts that capture AIA-specific metadata about both. Second is an algorithm that operates across all those artifacts to render a real-time prediction about whether or not the aggregate AI system or model complies with the AIA.
  arXiv  Detail & Related papers  (2024-06-20T22:07:15Z)
• The Artificial Intelligence Ontology: LLM-assisted construction of AI concept hierarchies [0.7796141041639462]
  The Artificial Intelligence Ontology (AIO) is a systematization of artificial intelligence (AI) concepts, methodologies, and their interrelations. AIO aims to address the rapidly evolving landscape of AI by providing a comprehensive framework that encompasses both technical and ethical aspects of AI technologies.
  arXiv  Detail & Related papers  (2024-04-03T20:08:15Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• AI-in-the-Loop -- The impact of HMI in AI-based Application [0.0]
  We introduce the AI-in-the-loop concept that combines AI's and humans' strengths. By enabling HMI during an AI uses inference, we will introduce the AI-in-the-loop concept that combines AI's and humans' strengths.
  arXiv  Detail & Related papers  (2023-03-21T00:04:33Z)
• Automated Machine Learning: A Case Study on Non-Intrusive Appliance Load Monitoring [81.06807079998117]
  We propose a novel approach to enable Automated Machine Learning (AutoML) for Non-Intrusive Appliance Load Monitoring (NIALM)<n>NIALM offers a cost-effective alternative to smart meters for measuring the energy consumption of electric devices and appliances.
  arXiv  Detail & Related papers  (2022-03-06T10:12:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.