Demonstrating chart-plot: Closing the Last Mile of Academic Chart Generation
2026-06-08 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors explain that while AI can write code to make charts, the real challenge is making those charts look professional and fit well into research papers. They created a system called chart-plot with three parts: one that learns the style of top journals, one that makes sure the chart fits nicely in the paper layout, and one that lets authors easily tweak every part of the chart. They tested this approach on different types of charts and with some user feedback. Their work focuses on improving the publishing step, not just generating chart code.
large language modelsmatplotlibchart code generationLaTeXfigure stylingrender loopdirect manipulationgrouped bar chartscaling line chartpaired distribution chart
Authors
Yinghao Tang, Yupeng Xie, Yingchaojie Feng, Jiale Lao, Tingfeng Lan, Wei Chen
Abstract
Large language models can translate a researcher's intent into runnable matplotlib code, yet the resulting chart rarely lands in a paper without multiple rounds of manual revision. We argue that the open problem is not chart code generation but chart publication: making the output look like a top-venue figure, survive the target layout, and respond to precise author edits. We present chart-plot, an agentic harness that closes this last mile through three components: (1) a style-aware code generator conditioned on a textual style skill distilled from accepted figures at the target venue, (2) a deployment-aware render loop that compiles the chart inside the target LaTeX context and revises until layout constraints are met, and (3) a structured edit layer that exposes every chart element as a directly manipulable handle. We report early results on three chart-type case studies (grouped bar, scaling line, paired distributions) and a small user study.