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

Junran Yang; Shruti Badrish; Teanna Barrett; Leilani Battle

cs.HCOct 8, 2026

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

Authors: Junran Yang, Shruti Badrish, Teanna Barrett, Leilani Battle

Organizations: University of Washington Seattle, Washington, USA

Abstract

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.

Figures & tables

Figure 1. The DAG interface, early in Anna’s session. The question bar (A) holds the analytical question the session started from and the control that parses it. The state DAG canvas (B) shows the claims Anna has formed, one node per candidate analysis. Here it holds the interpretations the parser returned, each labeled with the claim it makes, a natural-language rendering of what it would ask, the confidence that it is the intended reading, and its slots as chips. The moves available from each node hang beneath it, grouped by the state they would produce and collapsed to a count, so that the shape of what is still open is visible without enumerating it; the toolbar names the four families of move the grammar admits. The active node panel (C) describes the selected claim in full, lists its slots, and offers to complete it to a dashboard once its required slots are grounded. The knowledge graph (D) shows the concept layer and the data layer joined by bridge edges, with filters for which layers and edge types to display.

Figure 2. Anna’s intent graph at the end of her session, with the dashboards she has open and the node she has selected. Across the top are the three readings the parser returned for “What makes a movie successful?” Two paths A and B are outlined. Each outline encloses the claims Anna formed while following that reading, and the two enclose one card in common, the comparison of Rotten Tomatoes rating across genre that both readings resolve to. The move marked reshape is the one that changes the shape of the claim as it binds, which turns a relation into a comparison. The node panel at the right describes the selected claim A node is marked renderable once its slots reach data and it can be completed to a dashboard.

Figure 3. The DAG architecture, instantiated on “What makes movies successful?” The analyst’s question and the dataset schema are the only inputs. \footnotesize1⃝ Parsing the question seeds the intent graph \footnotesizeA⃝ with the claims it could resolve into, and \footnotesize2⃝ graph construction builds the knowledge graph \footnotesizeB⃝ from the question and the schema together. In the intent graph, each node is a claim whose slots carry a type, measurable (Q) or categorical (C), and a binding that is open, an unresolved concept, or a set of columns; a chart icon marks a node whose required slots are grounded and which therefore renders to a dashboard. The two edge families appear here as one descend step, which resolves “critical success” to the columns beneath it, and one reshape step, which turns a relationship into a comparison by admitting a categorical slot. The knowledge graph splits into a concept layer \footnotesizeC⃝, built once per question, and a data layer \footnotesizeD⃝, built once per dataset, joined by operationalized by bridge edges. The binding edge is where the two structures meet: grounding a slot is a walk from the concept a slot holds to the columns that operationalize it. The dashed “award” concept has no column to operationalize it, which the system reports rather than silently dropping.

multiset	$k$	$f$ : hypothesis	$g$ : template	example claim
{Q}	1	Value	M1	The distribution of worldwide gross.
{Q, Q}	2	Relation	M3	Production budget against worldwide gross.
{Q, C}	2	Comparison	CAT1 M2	Rotten Tomatoes rating across genre.
{Q, T}	2	Trend	CH1	Worldwide gross over release year.

Table 1. The reference instantiation of the typology, as the two tables behind

f

and

g

f

is defined only up to arity two: these four multisets are every base state the grammar admits.

g

is multi-valued where more than one framing is defensible; choosing among them is a render-time decision, not a production. Swapping these tables swaps the analytical vocabulary. Every analysis over three or more variables is a composite, given in Table 2 . Examples are drawn from the dataset of Section 4 .

composite	well-formed when	compiles to	example
$\text{Condition}(\textit{Spec},z)$	$z$ is categorical. It may be left open and bound afterwards.	A facet over $z$ : small multiples or a colour encoding; the CAT2 crosstab where the conditioned spec is a Comparison.	Does the budget–gross relation hold across genres?
$\text{Chain}(\textit{Spec},\textit{Spec},m)$	Both legs are Relations, both bind $m$ , and their remaining ends differ.	Two linked Relation panels, brushed on the shared $m$ .	Budget $\rightarrow$ vote count $\rightarrow$ worldwide gross.
$\text{Compare}(\textit{Spec},\dots)$	At least two legs, sharing a hypothesis type, pairwise distinct.	Overlay on the shared axis for Relations and for Trends, the latter giving CH2 ; a slope chart for Comparisons; side-by-side otherwise.	The box-office reading against the critical reading.

Table 2. The three composites of the reference instantiation, which extend the base states of Table 1 and are the only route to an analysis over three or more variables. Composites are not states and so have no image under

f

g

. Each carries a well-formedness condition that is relational , a property of how its sub-specs fit together that a single state cannot express, and each compiles to a qualitative layout over templates rather than to one template. The layouts subsume the multi-variable templates directly: a Condition over a Comparison yields the two-way CAT2 crosstab, and a Compare over two Trends sharing a time axis yields the CH2 dual-series chart. Examples are drawn from the dataset of Section 4 .

Explore similar work

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
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
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

May 8, 2026, cs.CYJ/K move · Enter open · S save

Business Utility of Large Language Models as Exploratory Data Analysis Agents

Rafał Łabędzki, Patryk Miziuła, Hubert Rutkowski, Szymon Betlewski+4

SGH Warsaw School of Economics · Bydgoszcz University of Science and Technology · At the time of contribution aﬀiliated with deepsense.ai, present aﬀiliation is Google

LLM Agent Evaluation AI Agent Benchmarks Supply Chain Management LLM Agent Reliability Data Analysis Agents

Open paper AskPDF arXiv

Large Language Models (LLMs) are increasingly used in analytical workflows, but their suitability as exploratory data analysis (EDA) agents in business settings remains uncertain. In practice, a deployable EDA agent must provide not only useful average performance but also sufficient repeatability to support trust in its outputs. We evaluate this requirement in a controlled, business-relevant benchmark built on an agent-based supply chain simulation. The task is to identify supplier-product combinations responsible for low quality and downstream sales loss by reasoning from indirect operational traces rather than from explicit labels. Fifteen model-variant configurations from eight model families were evaluated under four experimental conditions that varied data representation, prompt clarity, and signal strength, with five trajectories per condition. Outputs were scored against deterministic ground truth using the Jaccard index and assessed through a framework that combines mean score (ms), coefficient of variation (CV), exploratory cross-condition significance tests, and Business utility, a risk-adjusted metric that we propose to summarise quality and repeatability in a single operational measure. The results show that most configurations are not reliable enough for autonomous EDA use, even when their average scores appear acceptable. GPT-5.4 with extra-high reasoning effort achieved the strongest overall profile, with an experiment-averaged ms of 0.8748 and an experiment-averaged Business utility of 0.6952, while the next-best configurations lost substantially more utility after variability discounting. Our findings suggest that evaluation of EDA agents should treat average quality, repeatability, and condition sensitivity as complementary dimensions of operational trustworthiness.

Abstract

Explore similar work

Business Utility of Large Language Models as Exploratory Data Analysis Agents

DA-Studio: An Agentic System for End-to-End Data Analysis

DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis