TL;DR
The AgenticData system, an agentic data system that enables natural-language query analytics over heterogeneous data sources, is introduced and its ability to handle diverse data sources accurately and efficiently is illustrated.
This work presents DeepEye, a workflow-centric agentic data system that turns user intents into transparent and steerable analytical workflows and develops DataMagic as the system’s Video Generator, a declarative multi-agent method that improves data-video quality.
Databases are a crucial part of modern information systems, but interacting with them has traditionally required users to have some level of expertise in formal query languages. This barrier prevents non-technical users from getting the most out of the data that is stored. In this work, we propose a robust production oriented natural language interface that enables users to query document oriented Not Only SQL (NoSQL) databases (MongoDB) using natural language without requiring knowledge of complex query syntax. Unlike NL-to-SQL approaches, NL-to-MongoDB translation must handle evolving, nested document schemas and multi-stage aggregation pipelines, making schemaconsistent query generation and appropriate operator selection (e.g., match, group, lookup) error-prone. Our system addresses this via a modular agent pipeline comprising a Query Builder, Query Runner, and Response Synthesizer, combined with dual dynamic retrieval of relevant schema fragments and similar examples. This architecture allows for self-correction and efficient query generation at the enterprise scale. We evaluate our system on public NL-to-MongoDB benchmarks, including DocSpider and TEND, as well as proprietary datasets. Across DocSpider and TEND, our pipeline improves execution accuracy over prior baselines by up to 40% on DocSpider and 23% on TEND. These findings highlight the potential of our approach as an accessible and effective solution for natural language querying of document oriented NoSQL databases.
Experiments on public benchmarks and real-world industrial BI workloads show that QwenPaw-Data improves both verifiable data access capability and higher-level analytical quality, offering a practical foundation for reliable, traceable, and continuously improving enterprise data agents.
Agentic AI systems require world models that support reliable reasoning, planning, and decision-making under complex and heterogeneous conditions. Although heterogeneous graphs are natural candidates for this role, their structural design, particularly the selection of relational paths, is typically ad hoc and weakly governed from a semantic perspective, limiting robustness and interpretability. This paper proposes a semantic governance paradigm for heterogeneous world models, in which relational structures are explicitly constrained and validated at design time prior to learning. The paradigm is instantiated through Ontology-Driven Metapath Design (ODMD), which integrates ontological constraints, competency-based filtering, and lightweight predictive scoring to derive and select semantically admissible metapaths systematically. ODMD is integrated with a heterogeneous embedding pipeline, enabling the construction of governance-aware representations that combine node features, neighborhood aggregation, semantic information, and metapath-based encodings. An experimental evaluation on a multimodal heterogeneous graph shows that ontology-governed metapath design improves structural stability, semantic coherence, and robustness when compared to manual and brute-force alternatives. These results demonstrate that semantic governance provides a principled and practical foundation for agent-ready heterogeneous world models, supporting reusable, interpretable, and more reliable representations for proactive and autonomous AI systems.
It is argued that the key challenges are bridging the gap between personal and organizational memory, building effective agentic retrieval beyond naive RAG, and enabling organizations to evaluate their agents against their own data through self-serving evals.
Recent advances in large language models have enabled a new class of agentic data science systems that allow users to complete complex data science workflows through natural language. Although these systems can significantly reduce manual effort, it remains difficult to diagnose their behavior and steer the reasoning process when failures or unexpected outputs occur. We present MUSE, an interactive meta-agent that enhances user understanding and control of agentic data science systems by (1) dynamically restructuring low-level execution traces into multiple semantic levels that support navigation from high-level overviews to low-level implementation details; (2) enabling users to reference specific workflow steps in context to ask grounded questions, provide feedback, and revise problematic steps without manually locating relevant execution history; and (3) supporting mixed-initiative steering by surfacing suspicious steps for inspection, scaffolding the repair process, and translating user repair intent into contextualized instructions for the underlying agent. In a between-subjects study (n = 15), MUSE improved task efficiency and increased users'confidence in understanding and steering agentic data science workflows.