LLM-based data-analysis tools are increasingly used to help users analyze messy spreadsheets and workbooks, from answering questions over uploaded files to generating code, summaries, and visualizations. These systems are often evaluated by the correctness of their final downstream answers. However, reliable data analysis also depends on an earlier step: understanding what the dataset contains before solving the requested task. For complex workbooks, this Data Exploration step includes identifying the logical tables behind physical sheets, interpreting column semantics, recovering keys and relationships, and detecting quality issues. In current tools and benchmarks, this step is usually left implicit, creating a gap between downstream task performance and the dataset understanding needed for reliable, human-checkable analysis. Our key contribution is to identify this overlooked gap, make Data Exploration a first-class evaluation target, and show through downstream experiments that stronger Data Exploration support improves task performance. To evaluate dataset understanding directly, we introduce two benchmark settings: a real multi-sheet workbook benchmark based on a Vitamin D study dataset, and an extension of DSBench with schema-fixed Data Exploration artifacts. In both settings, systems are evaluated by the quality of a structured artifact capturing tables, columns, semantic roles, relationships, and profiling signals. Our results show that strong LLMs and data-analysis agents still miss important logical structure even when they read spreadsheet content. Furthermore, explicit Data Exploration support often improves downstream correctness, suggesting it should be treated as a first-class, inspectable stage in LLM data-analysis workflows and a natural human-in-the-loop checkpoint where domain experts can review and correct the artifact before downstream analysis proceeds.
Figures & tables
Figure 1. Typical LLM data-analysis workflows versus our proposed workflow with explicit Data Exploration.
Figure 2. We build on raw workbooks and the original downstream questions, and add an explicit Data Exploration layer.
Figure 3. Component-level Data Exploration benchmark scores on selected DSBench datasets, including table/column/relation matching and logical accuracy, profiling, outlier handling, LLM-judged summary quality, and overall structural score. Each panel reports means within one difficulty group.
Figure 4. Component-level Data Exploration benchmark scores on the real-world workbook. Scores include table/column/relation matching and logical accuracy, profiling, outlier handling, LLM-judged summary quality, and overall structural score.
Condition
What the system gets before downstream questions
Control
Raw files only
Middle
Raw files + the system’s own Data Exploration JSON (generated from the files)
Treatment
Raw files + oracle Data Exploration JSON (ground truth)
Table 1. Data Exploration as an intervention: three conditions used in our downstream experiments.
Figure 5. Accuracy on the real Vitamin D workbook experiments. Rows show tools and prompting conditions; the left column reports accuracy on dataset-understanding questions, and the right column reports accuracy on the downstream feature-table task (outputs evaluated as CSV files).
Figure 6. Mean accuracy of different tools in different conditions, grouped by difficulty.
Autonomous data analysis agents are increasingly expected to conduct exploratory analysis with limited human guidance about data. However, existing benchmarks typically evaluate such agents in prior-guided settings, providing selected data sources, explicit data schemas, or cleaned data, thereby understating the exploratory burden. To evaluate this realistic exploratory data analysis task, we introduce DataClawBench, a benchmark built from financial think-tank consulting scenarios where agents must independently explore unfamiliar, noisy, cross-domain data and produce verifiable conclusions. DataClawBench provides a unified real-world data environment with approximately 2.06 million records across enterprise, industry, and policy domains, with native data noise preserved. On top of this data environment, it defines 492 multi-step cross-domain tasks, each annotated with intermediate milestones that diagnose exploration and reasoning failures beyond outcome accuracy. A systematic evaluation of eight advanced LLMs under the OpenClaw agent reveals that exploratory data analysis breaks agent reliability: more exploration does not reliably translate into task-relevant progress or correct final answers.
Qiaohong Zhang, Weihao Ye, Jialong Chen +7
School of Computer Science and Engineering, Sun Yat-sen University · School of Software Engineering, Sun Yat-sen University · Lingnan College, Sun Yat-sen University
Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate isolated operations such as single-formula generation or local cell edits, and therefore fail to capture end-to-end workflows in realistic business settings. We introduce SpreadsheetBench 2, a workflow-level benchmark for spreadsheet agents that covers three task categories: generation, debugging, and visualization. The benchmark is constructed from authentic business data, including financial reports and corporate filings, and is annotated and validated by domain experts. The benchmark contains 321 tasks; each instance averages 11.8 worksheets and requires 593.5 cell modifications, reflecting large multi-sheet workbooks with cross-sheet dependencies. We evaluate eight frontier large language models under a unified multi-turn agent scaffold, and additionally include several LLM-based spreadsheet products as complementary baselines. Results show that current systems remain far from reliable on real-world workflows: the best model achieves 34.89% overall task accuracy, and debugging accuracy is as low as 12.00%. Trajectory analysis and a failure taxonomy further indicate that insufficient spreadsheet inspection and incorrect target-cell selection are the dominant bottlenecks. Together, these findings position SpreadsheetBench 2 as a challenging testbed for advancing reliable spreadsheet automation. Project page: https://spreadsheetbench.github.io/
Jian Zhu, Yuzheng Zhang, Zeyao Ma +11
School of Information, Renmin University of China · Aptura AI · Shortcut AI +1
Spreadsheets and tables are widely used representations for structured data analysis, but effective analysis still requires substantial manual effort and domain expertise. Recent large language model (LLM) agents can automate parts of this process, but they often provide limited transparency into intermediate decisions, rely on implicit assumptions, struggle with multi-table comparison, and repeat similar workflows without adapting to a user's preferences. This paper presents TabClaw, an open-source interactive AI agent for spreadsheet manipulation and table reasoning. Users upload CSV or Excel files and issue natural-language requests; TabClaw clarifies ambiguous intent, exposes an editable execution plan, streams a ReAct-style tool-using analysis loop, dispatches specialist agents for parallel multi-table reasoning, and synthesizes findings with explicit consensus and uncertainty markers. Beyond one-off analysis, TabClaw records completed workflows, extracts persistent user memory, distills reusable skills from repeated tool-use patterns, supports package-style skill import, and upgrades skills from negative feedback. Experiments on spreadsheet manipulation and table reasoning benchmarks show that TabClaw improves executable task completion and reasoning performance while preserving an inspectable user workflow. This paper shows how TabClaw turns spreadsheets and tables into inspectable analytical workflows while gradually personalizing itself to recurring data-analysis tasks. Our code is available.
Mingyue Cheng, Shuo Yu, Daoyu Wang +5
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China