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.

From Questions to Queries to Insights: A Schema-Grounded Agentic Workflow for Natural-Language Crash Data Analysis
Oct 26, 2026Jingwen Zhu, Keshu Wu, Steven T. Parker +2Data Analysis Agents Execution-Guided Text-to-SQL
Department of Civil and Environmental Engineering, University of Wisconsin–Madison, Madison, WI, United States
Semantic Atoms for Scalable Text Analysis in Data Analytics in the Era of LLM-Based Agents
Oct 26, 2026Jinxiang Xie, Zihao Li, Rui Ding +3Data Analysis Agents LLM Agent Efficiency
Nanjing University · Tsinghua University · Microsoft Research
AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
Oct 23, 2026Atharva Naik, Vivek Chari, Pol Llado +5Data Analysis Agents Process Reward Models
Carnegie Mellon University · Microsoft
DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks
Oct 23, 2026Shan Peng, Shuaiqi Cheng, Miao Peng +2LLM Decision-Making Process-Based Agent Evaluation
Xiwei Technology (Guangzhou) Co., Ltd. · The Hong Kong University of Science and Technology (Guangzhou)
Toward an Agentic AI Approach to Public Health Data Collection
Oct 22, 2026Xueyi Zhang, Hongru Du, Ensheng DongData Analysis Agents Multi-Agent Systems
Department of Systems and Information Engineering, University of Virginia, Charlottesville, USA · Engineering and Applied Sciences Department, RAND, Arlington, USA
Charts as Epistemic Actions for Experience-Driven Agentic Data Analysis
Oct 21, 2026Xinzhe Wang, Xudong Weng, Zang Li +1Data Analysis Agents LLM Agent Skill Learning
Tencent · Renmin University of China
The Data Differentiator Framework (DDF): Quantifying Marginal Data Value with Information-Theoretic and Game-Theoretic Measures in an Agentic Evaluation Pipeline (SDSAE)
Oct 20, 2026Sukesh Kumar, Dilip SinghData Valuation Data Analysis Agents
Equifax Inc.
Unsupervised Tool Evolution for Coding Agents in Data-Lake Analytics
Oct 19, 2026Yuqing Yang, Yurong Liu, Deqing Fu +5AI Coding Agents LLM Agent Self-Improvement
University of Southern California · Google · New York University
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
Oct 17, 2026Nan Jia, Wenxuan Shi, Jingqing Ruan +11Data Analysis Agents Synthetic Data Generation for LLM Agents
Huazhong University of Science and Technology · Institute of Computing Technology, Chinese Academy of Sciences · Meituan +3
AgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics
Oct 16, 2026Dayan Pan, Bincheng Zuo, Xiaojian Wang +2Enterprise Analytics Data Analysis Agents
School of Computer Science and Engineering, Beihang University, Beijing, China · Omaha AIGC, Shanghai, China
Data World: Scaling Data Environments from Scratch
Oct 15, 2026Zhanli Li, Zeyuan Xu, Chaoxu Pang +16Synthetic Data Generation for LLM Agents Data Analysis Agents
Longcat Interaction Team, Meituan · Zhongnan University of Economics and Law · Hunan University +7
Same Context, Different Agents: A Behavioral Study of Semantic Layers, Multi-Agent Orchestration and Memory Compaction in Data Agents
Oct 14, 2026Zhivar Sourati, Marianne Menglin Liu, Zheng Wang +6Context Compaction for LLM Agents LLM Agents
University of Southern California · Oracle AI · University of Pennsylvania
Searching for What Matters: Open-Ended Discovery of Multiple Hypotheses with Agentic Data Exploration
Oct 13, 2026Sanchit Kabra, Nurendra Choudhary, Jiangshu Du +3Scientific Hypothesis Generation Data Analysis Agents
Virginia Tech · Amazon
LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement
Oct 10, 2026Ruichen Xia, Xiao Han, Dingyu Yang +5LLM-Based Program Synthesis Text-to-SQL
The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · Institute of Computing Innovation, Zhejiang University, Hangzhou, China · Zhejiang Geely Holding Group Co., Ltd., Hangzhou, China
The Silent Failures in Agentic Data Science
Oct 9, 2026Xue Li, Hongqian Xia, Daniel Gomm +3Data Analysis Agents LLM Agent Evaluation
Centrum Wiskunde & Informatica, Amsterdam, Netherlands
From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysis
Oct 7, 2026Raviraja G, Viraj Bagal, Prabhath ChellingiData Analysis Agents LLM Agent Evaluation
Enterpret
DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis
Oct 7, 2026Yizhi Song, Hang Ni, Weijia Zhang +1Data Analysis Agents AI Agent Benchmarks
The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China
BioStudyBench: Evaluating Agents on Post-Cutoff Biomedical Studies
Oct 6, 2026David Li, Shaamil Karim, Christian GensbiglerScientific Agent Benchmarks AI Agent Benchmarks
University of Waterloo
A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain
Oct 2, 2026Yiou Wu, Zezhi Tang, Ningwei Bai +1Data Analysis Agents LLM Agent Orchestration
Department of Computer Science, University College London, London, United Kingdom
FinNextAssist: Towards Professional Financial Deep Research Assistant
Oct 2, 2026Xiangyu Li, Fengbin Zhu, Xuan Yao +9Deep Research Agents Data Analysis Agents
South China University of Technology · National University of Singapore · iFLYTEK CO., LTD +3
DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis
Oct 2, 2026Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko +10Data Analysis Agents Text-to-SQL
Virginia Tech, VA, USA. · The Chronicle of Higher Education, Washington, DC, USA
ArrivalBench: Agent-Generated Data Pipelines Are Correct Once and Wrong Under Time
Oct 1, 2026Pranay KothariAI Agent Benchmarks LLM Agent Evaluation
Department of Computer Science, University of Oxford
Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows
Oct 1, 2026Gabriel Tomitsuka, Arman Raayatsanati, Emma Xing +2Enterprise Analytics AI Agent Benchmarks
TextQL
OceanMind: A multi-agent AI system for ocean diagnosis
Sep 30, 2026Fan Zhang, Weicong Cheng, Yuheng Chen +6Data Analysis Agents Multi-Agent LLM Systems
Department of Mathematics, The Hong Kong University of Science and Technology, Hong Kong SAR, China. · Center for Ocean Research in Hong Kong and Macau, The Hong Kong University of Science and Technology, Hong Kong SAR, China. · Department of Ocean Science, The Hong Kong University of Science and Technology, Hong Kong SAR, China.
Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses
Sep 28, 2026Huachi Zhou, Yujing Zhang, Jiahe Du +7LLM Agent Harnesses LLM Agent Reliability
The Hong Kong Polytechnic University, Hong Kong, China · Jilin University, Changchun, China
StateGuard: Analytical-State Management with Validity-Aware Intervention for Long-Horizon Data Agents
Sep 28, 2026Wenle Liao, Zhao Wang, Jingchao Zhang +3LLM Agent Verification Graph-Based Agent Memory
Gaoling School of Artificial Intelligence Renmin University of China
DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?
Sep 27, 2026Nan Huang, Mario Tapia-Pacheco, Kun Zhou +4AI Agent Reliability Scientific Hypothesis Generation
University of California San Diego · Independent Researcher
Fail Loudly: An Auditable Runtime for Agentic Data Analysis
Sep 26, 2026Hanxu Yan, Langxuan Deng, Zhengle Wang +2Runtime Enforcement for AI Agents Data Analysis Agents
Independent Researcher · Purdue University
DashAct: A Progressive Diagnostic Benchmark for GUI Agents in Interactive Dashboard Analysis
Sep 26, 2026Chuhan Zhang, Qi Xie, Ziyue Wang +4GUI Agent Benchmarks GUI Agents
State Key Laboratory of CAD&CG, Zhejiang University · College of Computer Science and Technology, Zhejiang University
LaMET-Agent: An Agent Framework for Large-Momentum Effective Theory Analysis
Sep 26, 2026Jinchen He, Xiangyu Jiang, Fei Yao +1High-Energy Physics Data Analysis Agents
Fermi National Accelerator Laboratory, Batavia, IL 60510, USA · Maryland Center for Fundamental Physics, University of Maryland, College Park, MD 20742, USA · Physics Division, Argonne National Laboratory, Lemont, IL 60439, USA +3

Oct 26, 2026J/K move · Enter open · S save

From Questions to Queries to Insights: A Schema-Grounded Agentic Workflow for Natural-Language Crash Data Analysis

Jingwen Zhu, Keshu Wu, Steven T. Parker, Bin Ran+1

Department of Civil and Environmental Engineering, University of Wisconsin–Madison, Madison, WI, United States

Data Analysis Agents Execution-Guided Text-to-SQL Text-to-SQL Evaluation LLM Agent Verification

Open paper AskPDF arXiv

Transportation agencies maintain extensive crash databases to identify safety priorities, evaluate countermeasures, and guide resource allocation. Making these data accessible to practitioners requires flexible ways to translate analytical questions into reliable results. Existing dashboards support predefined analyses, while additional requests often depend on specialists who understand database queries, coded fields, and agency conventions. This study presents CrashDB-QA, a fully local, schema-grounded agentic workflow that enables natural-language analysis of crash databases. Specialized components interpret questions, generate and validate read-only SQL, execute queries, and explain the results. A shared knowledge base grounds query construction in the agency's data dictionary and safety-analysis conventions, while recorded intermediate outputs support inspection and auditing. An optional extension, CrashDB-QA+, checks the alignment among the question, query, and execution result and supplies evidence for iterative repair. We evaluate the workflow on a frozen snapshot of 4.4 million Wisconsin crash records using a new benchmark of 300 questions across ten analytical categories and nine local open-weight models. Domain grounding substantially improves query accuracy, and a code-specialized 7B model provides the best accuracy-latency balance among the tested models. Compositional analyses remain more difficult than routine retrieval, particularly comparisons between groups or periods. Verification improves performance when the Judge uses authoritative field definitions and the Refiner receives execution evidence, whereas additional checking alone offers no consistent benefit. These findings demonstrate the potential of locally deployed, domain-grounded workflows to broaden access to crash analysis and identify the reasoning and verification capabilities needed for reliable use.