Data Analysis Agents

Follow this topic Ask about this topic

Data analysis agents combine language-model planning with tools such as Python, SQL, statistical packages, APIs, and visualization software to investigate data and explain results. Common approaches include code-generating agents, specialized multi-agent workflows, and systems grounded in schemas, ontologies, or domain-specific skills. Work spans business intelligence, spreadsheets, scientific research, and clinical or financial analysis, with growing emphasis on sandboxed execution, verification, provenance, and human oversight. Agents can handle bounded tasks, but ambiguity, long-running state, cross-source evidence, and silent methodological errors remain major challenges, as do evaluations that measure trustworthy end-to-end results rather than plausible outputs alone.

Latest papers

106 papers24 papers in the last four weeks, up 26% on the four weeks before. 0.1% of all new papers.

AgenticDataBench: A Comprehensive Benchmark for Data Agents
Jul 2, 2026Zhaoyan Sun, Shan Zhong, Daizhou Wen +10LLM Agent Evaluation AI Agent Benchmarks
Tsinghua University · Ant Digital Technologies, Ant Group
DA-Studio: An Agentic System for End-to-End Data Analysis
Jun 30, 2026Yizhe Liu, Shaolei Zhang, Ju FanExecution-Guided Code Generation Agentic Workflows
Renmin University of China
Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System
Jun 23, 2026Tian Zheng, Kai-Tai HsuLLM-as-a-Judge Human-in-the-Loop Evaluation
Department of Statistics Columbia University New York, NY
VeriGraph: Towards Verifiable Data-Analytic Agents
Jun 15, 2026Jiajie Jin, Zhao Yang, Wenle Liao +5Data Provenance Neuro-Symbolic Reasoning
Gaoling School of Artificial Intelligence, Renmin University of China
Fantastic Scientific Agents and How to Build Them: AgentBuild for Rietveld Refinement
Jun 11, 2026Woong Shin, Craig A. Bridges, Marshall T. McDonnell +1AI Agents for Scientific Discovery LLM Agent Self-Improvement
Oak Ridge National Laboratory, Oak Ridge, TN, USA
GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models
Jun 11, 2026Gabriel Diaz-Ireland, Diego Prieto-Herráez, Mario García Peces +2LLM Agent Evaluation Geospatial Reasoning
Universidad Católica de Ávila (UCAV) Ávila, Spain · Johns Hopkins University Baltimore, MD, USA · Independent Researcher Madrid, Spain +1
TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning
Jun 9, 2026Mingyue Cheng, Shuo Yu, Daoyu Wang +5Multi-Agent LLM Systems Table Reasoning
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
Unsupervised Skill Discovery for Agentic Data Analysis
Jun 4, 2026Zhisong Qiu, Kangqi Song, Shengwei Tang +4LLM Agent Skill Learning Agent Skill Learning
Zhejiang University · Ant Group
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis
May 28, 2026Kewei Xu, Xiaoben Lu, Shuofei Qiao +4Long-Horizon Agent Evaluation Long-Horizon Agent Tasks
Zhejiang University · Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph · Ant Group
AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery
May 22, 2026Darek Kleczek, Fuheng Zhao, Alexander W. Lee +4AI Agent Evaluation AI Agent Benchmarks
Snowflake · Brown University and Snowflake
Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks
May 20, 2026Haichao Miao, Zhimin Li, Kuangshi Ai +4Scientific Visualization Data Visualization
Lawrence Livermore National Laboratory · Vanderbilt University · University of Notre Dame
Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents
May 10, 2026Josefa Lia Stoisser, Marc Boubnovski Martell, Sidsel Boldsen +2LLM Agent Evaluation AI Agent Benchmarks
Novo Nordisk London, UK
RelAgent: LLM Agents as Data Scientists for Relational Learning
May 8, 2026Xingyue Huang, Louis Tichelman, Jinwoo Kim +2Interpretable ML LLM Agents
University of Oxford · TU Wien · AITHYRA +1
Business Utility of Large Language Models as Exploratory Data Analysis Agents
May 8, 2026Rafał Łabędzki, Patryk Miziuła, Hubert Rutkowski +5LLM Agent Evaluation AI Agent Benchmarks
SGH Warsaw School of Economics · Bydgoszcz University of Science and Technology · At the time of contribution aﬀiliated with deepsense.ai, present aﬀiliation is Google
Agentic-imodels: Evolving agentic interpretability tools via autoresearch
May 5, 2026Chandan Singh, Yan Shuo Tan, Weijia Xu +4Interpretable ML Automated Machine Learning
Microsoft Research · National University of Singapore
DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis
May 4, 2026Qiaohong Zhang, Weihao Ye, Jialong Chen +7LLM Agent Reliability Agent Benchmarks
School of Computer Science and Engineering, Sun Yat-sen University · School of Software Engineering, Sun Yat-sen University · Lingnan College, Sun Yat-sen University
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
Apr 27, 2026Zhisong Qiu, Shuofei Qiao, Kewei Xu +4Process Reward Models RL for LLM Agents
Zhejiang University Ant Group Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph Hangzhou, China · Zhejiang University Hangzhou, China · Ant Group Hangzhou, China +2
Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis
Apr 24, 2026Junyan Cheng, Kyle Richardson, Peter ChinLLM Agent Orchestration LLM Agents
Dartmouth Collegeα · Allen Institute for AIβ
QRAFTI: An Agentic Framework for Empirical Research in Quantitative Finance
Apr 20, 2026Terence Lim, Kumar Muthuraman, Michael SuryQuantitative Finance Multi-Agent Collaboration
Graphen Inc. · The University of Texas at Austin
Demonstration of Pneuma-Seeker: Agentic System for Reifying and Fulfilling Information Needs on Tabular Data
Apr 15, 2026Muhammad Imam Luthfi Balaka, Raul Castro FernandezData Analysis Agents Agentic Retrieval
The University of Chicago, Chicago, USA
Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research
Apr 14, 2026Taehun Kim, Hyeryun Park, Hyeonhoon Lee +3AI-Assisted Scientific Research Data Analysis Agents
Infmedix, Co., Ltd., Seoul, Republic of Korea. · Department of Transdisciplinary Studies, Seoul National University, Seoul, Republic of Korea. · Healthcare AI Research Institute, Seoul National University Hospital, Seoul, Republic of Korea. +3
Sanity Checks for Agentic Data Science
Apr 13, 2026Zachary T. Rewolinski, Austin V. Zane, Hao Huang +4AI Agent Reliability Data Analysis Agents
Dept. of Statistics, UC Berkeley · Dept. of EECS, UC Berkeley · Microsoft Research +1
Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning
Apr 12, 2026Xinyi HuangKnowledge Augmentation for Language Models Retrieval-Augmented Generation
Simon Fraser University
DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling
Apr 7, 2026Shicheng Liu, Yucheng Jiang, Sajid Farook +3Data Analysis Agents Deep Research Agents
Computer Science Department, Stanford University, Stanford, CA
Owl-AuraID 1.0: An Intelligent System for Autonomous Scientific Instrumentation and Scientific Data Analysis
Mar 31, 2026Han Deng, Anqi Zou, Hanling Zhang +14Laboratory Automation Scientific Workflow Automation
Shenzhen Loop Area Institute, Shenzhen, China. · The Chinese University of Hong Kong, Hong Kong. · Dalian University of Technology, Dalian, China. +2
SentinelAI: A Multi-Agent Framework for Structuring and Linking NG9-1-1 Emergency Incident Data
Mar 25, 2026Kliment Ho, Ilya ZaslavskyDisaster Response Data Analysis Agents
San Diego Supercomputer Center UC San Diego La Jolla, CA
AI Agents Can Already Autonomously Perform Experimental High Energy Physics
Mar 20, 2026Eric A. Moreno, Samuel Bright-Thonney, Andrzej Novak +2Autonomous Research Agents AI Agents for Scientific Discovery
Department of Physics, Massachusetts Institute of Technology · NSF AI Institute for Artificial Intelligence and Fundamental Interactions · CERN
AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
Mar 19, 2026An Luo, Jin Du, Xun Xian +12AI Agent Evaluation AI Agent Benchmarks
School of Statistics, University of Minnesota · AIScientists, Inc. · Data Science Institute, University of Chicago +4
PMAx: An Agentic Framework for AI-Driven Process Mining
Mar 16, 2026Anton Antonov, Humam Kourani, Alessandro Berti +2Process Mining Data Analysis Agents
Fraunhofer Institute for Applied Information Technology FIT, Schloss Birlinghoven, 53757 Sankt Augustin, Germany · RWTH Aachen University, Ahornstraße 55, 52074 Aachen, Germany
ClimateAgents: A Multi-Agent Research Assistant for Social-Climate Dynamics Analysis
Mar 14, 2026Shan ShanAutonomous Research Agents Data Analysis Agents

Jul 2, 2026J/K move · Enter open · S save

AgenticDataBench: A Comprehensive Benchmark for Data Agents

Zhaoyan Sun, Shan Zhong, Daizhou Wen, Jiaxing Han+9

Tsinghua University · Ant Digital Technologies, Ant Group

LLM Agent Evaluation AI Agent Benchmarks Synthetic Benchmark Generation Data Analysis Agents

Open paper AskPDF arXiv

Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process is essential to reducing labor-intensive efforts for data scientists and enabling scalable data-driven applications. Recently, large language model (LLM)-based data agents have emerged as a promising solution to automate data science workflows. However, the field lacks comprehensive benchmarks to rigorously evaluate these agents across diverse scenarios with fine-grained granularity. To address this gap, we propose AgenticDataBench, a comprehensive benchmark featuring realistic tasks spanning diverse domains with fine-grained ground-truth labels. This enables evaluations to capture the diversity and complexity of data science workflows and the detailed performance of agents. First, to cover diverse domains, we collect real datasets and tasks from 15 vertical domains, including 5 real-world B2B use cases from a leading fintech company. Second, to remove redundancy in real-world tasks and generate high-quality tasks for domains lacking real data, we introduce data science skills, recurring data-centric operational patterns, and quantify benchmark coverage by the number of skills included. Representative skills are extracted from large-scale task solutions on Stack Overflow using skill-aligned hierarchical clustering. Third, for real-world business tasks, we select task-solution pairs that maximize diversity in skill composition, ensuring broad coverage of practical scenarios. Fourth, to generate realistic tasks for devise domains without real tasks, we propose a systematic LLM-based task generation approach to create workflows and tasks based on these skills. Finally, we evaluate state-of-the-art data agents using our annotated benchmark and open-sourced testbed, providing detailed skill-level insights.