相关论文: Building a Correct-by-Design Lakehouse. Data Contr…

AI agents are increasingly the primary consumers of data, operating continuously to make concurrent, irreversible decisions. Traditional data systems designed for human analysis cycles become correctness bottlenecks under this operating…

With the growing popularity of Large Reasoning Models and their results in solving mathematical problems, it becomes crucial to measure their capabilities. We introduce a pipeline for both automatic and interactive verification as a more…

Constructing Extract-Load-Transform (ELT) pipelines is a labor-intensive data engineering task and a high-impact target for AI automation. On ELT-Bench, the first benchmark for end-to-end ELT pipeline construction, AI agents initially…

Code-generating LLMs are trained largely on static artifacts (source, comments, specifications) and rarely on materializations of run-time behavior. As a result, they readily internalize buggy or mislabeled code. Since non-trivial semantic…

Data management can be a complex challenge in fields such as bioinformatics and health sciences, which continuously generate extensive heterogeneous datasets. In the context of collaborative global health initiatives, secure storage and…

Traditional Data+AI systems utilize data-driven techniques to optimize performance, but they rely heavily on human experts to orchestrate system pipelines, enabling them to adapt to changes in data, queries, tasks, and environments. For…

Text-to-SQL systems provide a natural language interface that can enable even laymen to access information stored in databases. However, existing Large Language Models (LLM) struggle with SQL generation from natural instructions due to…

Complex data pipelines are increasingly common in diverse applications such as BI reporting and ML modeling. These pipelines often recur regularly (e.g., daily or weekly), as BI reports need to be refreshed, and ML models need to be…

In the rapidly evolving landscape of digital assets and blockchain technologies, the necessity for robust, scalable, and secure data management platforms has never been more critical. This paper introduces a novel software architecture…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

In the last few years, the concept of data lake has become trendy for data storage and analysis. Thus, several design alternatives have been proposed to build data lake systems. However, these proposals are difficult to evaluate as there…

Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…

This article presents a modular, component-based architecture for developing and evaluating AI agents that bridge the gap between natural language interfaces and complex enterprise data warehouses. The system directly addresses core…

Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different…

GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc…

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…

The growing integration of machine learning (ML) and artificial intelligence (AI) models into high-stakes domains such as healthcare and scientific research calls for models that are not only accurate but also interpretable. Among the…

The rapid development of AI and LLMs has driven new methods of SDLC, in which a large portion of code, technical, and business documentation is generated automatically. However, since there is no single architectural framework that can…

Analysis pipelines commonly use high-level technologies that are popular when created, but are unlikely to be readable, executable, or sustainable in the long term. A set of criteria is introduced to address this problem: Completeness (no…