# Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis

arXiv: https://arxiv.org/abs/2610.11025 · HTML: https://mlsanity.com/paper/2610.11025/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 107 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 17 of 17)

- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [Data-driven Discovery with Large Generative Models](https://mlsanity.com/paper/2402.13610/) (2024)
- [Calliope: Automatic Visual Data Story Generation from a Spreadsheet](https://mlsanity.com/paper/2010.09975/) (2020)
- [Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration System](https://mlsanity.com/paper/2304.00477/) (2023)
- [ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization](https://mlsanity.com/paper/2403.11236/) (2024)
- [Goals, Process, and Challenges of Exploratory Data Analysis: An Interview Study](https://mlsanity.com/paper/1911.00568/) (2019)
- [Lux: Always-on Visualization Recommendations for Exploratory Dataframe Workflows](https://mlsanity.com/paper/2105.00121/) (2021)
- [DashBot: Insight-Driven Dashboard Generation Based on Deep Reinforcement Learning](https://mlsanity.com/paper/2208.01232/) (2022)
- [Generating Analytic Specifications for Data Visualization from Natural Language Queries using Large Language Models](https://mlsanity.com/paper/2408.13391/) (2024)
- [Charting EDA: Characterizing Interactive Visualization Use in Computational Notebooks with a Mixed-Methods Formalism](https://mlsanity.com/paper/2409.10450/) (2024)
- [Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale](https://mlsanity.com/paper/2504.09283/) (2025)
- [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://mlsanity.com/paper/2602.16844/) (2026)
- [A Grammar of Hypotheses for Visualization, Data, and Analysis](https://mlsanity.com/paper/2204.14267/) (2022)
- [LINX: A Language Driven Generative System for Goal-Oriented Automated Data Exploration](https://mlsanity.com/paper/2406.05107/) (2024)
- [Flowco: Rethinking Data Analysis in the Age of LLMs](https://mlsanity.com/paper/2504.14038/) (2025)
- [VisCanvas: A Node-Based Interface for Exploratory Visualization Authoring with LLMs](https://mlsanity.com/paper/2607.21886/) (2026)

## Abstract (arXiv)

Exploratory data analysis (EDA) is rarely open-ended in practice: analysts work from high-level domain questions toward the concrete analyses that can answer them, prioritizing directions with domain knowledge and prior hypotheses. Large language models (LLMs) can supply such knowledge, but their responses are unstructured, leaving analysts no way to see what has been explored, what is missing, or why one direction was chosen over another. We present DAG-EDA, a system that lets analysts and an LLM co-navigate the space of possible analyses through two linked structures. An intent graph, governed by a grammar of analytical intent, decomposes an ambiguous natural-language question into progressively concrete analysis tasks, keeping alternative framings open and letting analysts branch, backtrack, and compare paths. A multi-layered knowledge graph externalizes the LLM's domain knowledge, linking domain concepts to the dataset variables that can measure them, so analysts can inspect and contest how their question is grounded in the data. Both graphs are constructed from only the dataset and the analyst's question, and the analyses the analyst reaches are rendered as interactive dashboards. We illustrate the system through a usage scenario and describe a user study design for examining whether the system scaffold analysts' reasoning and navigation.