# AgenticData: An Agentic Data Analytics System for Heterogeneous Data arXiv: https://arxiv.org/abs/2508.05002 ยท HTML: https://mlsanity.com/paper/2508.05002/ ## Key facts - Cited by 22 papers in the map (data through 14 Oct 2026). - Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. - Builds on 18 of its 38 references that are in the map. - First posted on arXiv 7 Aug 2025. ## Placed in - LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/) ## Builds on (most cited first, 18 of 18) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024) - [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022) - [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024) - [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025) - [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024) - [A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?](https://mlsanity.com/paper/2408.05109/) (2024) - [Named Entity Recognition and Classification on Historical Documents: A Survey](https://mlsanity.com/paper/2109.11406/) (2021) - [DABstep: Data Agent Benchmark for Multi-step Reasoning](https://mlsanity.com/paper/2506.23719/) (2025) - [ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration](https://mlsanity.com/paper/2502.00675/) (2025) - [Text2SQL is Not Enough: Unifying AI and Databases with TAG](https://mlsanity.com/paper/2408.14717/) (2024) - [Towards Optimizing the Costs of LLM Usage](https://mlsanity.com/paper/2402.01742/) (2024) - [From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent](https://mlsanity.com/paper/2505.02024/) (2025) - [KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes](https://mlsanity.com/paper/2506.06541/) (2025) - [UQE: A Query Engine for Unstructured Databases](https://mlsanity.com/paper/2407.09522/) (2024) - [CAESURA: Language Models as Multi-Modal Query Planners](https://mlsanity.com/paper/2308.03424/) (2023) - [Abacus: A Cost-Based Optimizer for Semantic Operator Systems](https://mlsanity.com/paper/2505.14661/) (2025) - [Towards Accurate and Efficient Document Analytics with Large Language Models](https://mlsanity.com/paper/2405.04674/) (2024) ## Built on by (most cited first, 22 of 22) - [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025) - [AgentSM: Semantic Memory for Agentic Text-to-SQL](https://mlsanity.com/paper/2601.15709/) (2026) - [Scaling Generalist Data-Analytic Agents](https://mlsanity.com/paper/2509.25084/) (2025) - [Arming Data Agents with Tribal Knowledge](https://mlsanity.com/paper/2602.13521/) (2026) - [AgenticDataBench: A Comprehensive Benchmark for Data Agents](https://mlsanity.com/paper/2607.01647/) (2026) - [Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis](https://mlsanity.com/paper/2604.24198/) (2026) - [OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning](https://mlsanity.com/paper/2510.23870/) (2025) - [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026) - [DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces](https://mlsanity.com/paper/2608.03451/) (2026) - [An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data](https://mlsanity.com/paper/2603.07841/) (2026) - [Unsupervised Skill Discovery for Agentic Data Analysis](https://mlsanity.com/paper/2606.06416/) (2026) - [Access Paths for Efficient Ordering with Large Language Models](https://mlsanity.com/paper/2509.00303/) (2025) - [Analytical Search](https://mlsanity.com/paper/2602.11581/) (2026) - [stratum: A System Infrastructure for Massive Agent-Centric ML Workloads](https://mlsanity.com/paper/2603.03589/) (2026) - [PExA: Parallel Exploration Agent for Complex Text-to-SQL](https://mlsanity.com/paper/2604.22934/) (2026) - [Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systems](https://mlsanity.com/paper/2605.27571/) (2026) - [SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing](https://mlsanity.com/paper/2606.11424/) (2026) - [AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis](https://mlsanity.com/paper/2608.17834/) (2026) - [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026) - [Fail Loudly: An Auditable Runtime for Agentic Data Analysis](https://mlsanity.com/paper/2609.32528/) (2026) - [Robust Hierarchical Structures for Agentic Document Analysis](https://mlsanity.com/paper/2609.33322/) (2026) - [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026) ## Abstract (arXiv) Existing unstructured data analytics systems rely on experts to write code and manage complex analysis workflows, making them both expensive and time-consuming. To address these challenges, we introduce AgenticData, an innovative agentic data analytics system that allows users to simply pose natural language (NL) questions while autonomously analyzing data sources across multiple domains, including both unstructured and structured data. First, AgenticData employs a feedback-driven planning technique that automatically converts an NL query into a semantic plan composed of relational and semantic operators. We propose a multi-agent collaboration strategy by utilizing a data profiling agent for discovering relevant data, a semantic cross-validation agent for iterative optimization based on feedback, and a smart memory agent for maintaining short-term context and long-term knowledge. Second, we propose a semantic optimization model to refine and execute semantic plans effectively. Our system, AgenticData, has been tested using three benchmarks. Experimental results showed that AgenticData achieved superior accuracy on both easy and difficult tasks, significantly outperforming state-of-the-art methods.