Thinkink: 2D Spatial Ink-native Interaction with LLMs

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Mohammad Hasan Payandeh, Daniel Vogel, Jian Zhao
• Venue: arXiv: cs.HC
• Published: 2026-07-23
• Collected: 2026-07-24
• URL: http://arxiv.org/abs/2607.21468v1
• PDF: https://arxiv.org/pdf/2607.21468v1
• DOI: UNKNOWN

Plain-Language Brief

The researchers proposed a new tool called Thinkink that integrates large language models (LLMs) into handwritten note-taking and sketching practices. The tool allows users to handwrite or draw on a shared canvas, with LLM-generated responses displayed as ink-like text and sketches. A semantic tree is used to interpret the ink, and a lightweight UI provides control using a state machine. The development of Thinkink was informed by three studies, examining current practices, usability challenges, and how people incorporate it into their ideation practices.

What the Document Says

• The researchers proposed a tool called Thinkink.
• Thinkink integrates large language models (LLMs) into handwritten note-taking and sketching.
• Users can handwrite or draw on a shared canvas.
• LLM-generated responses are displayed as ink-like text and sketches.
• A semantic tree is used for ink interpretation.
• A lightweight UI provides control using a state machine.
• The development of Thinkink was informed by three studies.

Key Concepts Mentioned

• Thinkink
• Large Language Models (LLMs)
• handwritten notes
• sketches
• shared canvas
• semantic tree
• lightweight UI
• state machine

Claims Made by the Document

• Thinkink is a tool that integrates LLMs into handwritten note-taking and sketching.
• The development of Thinkink was informed by three studies.

Evidence Used

• People often use handwritten notes and sketches to externalize ideas for ideation.
• The semantic tree streamlines ink interpretation.
• A lightweight UI provides explicit control using a state machine.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

People often use handwritten notes and sketches to externalize ideas for ideation. To integrate large language models (LLMs) into this practice, we propose Thinkink. Prompts can be handwritten text or drawn sketches with LLM-generated responses visualized as ink-like text and sketches spatially integrated into a shared canvas. A semantic tree streamlines ink interpretation, and a lightweight UI provides explicit control using a state machine. The tool was designed using a three-stage process. A formative study (N=12) examined current practices with conventional and digital inking methods. The results informed a technical probe for a diagnostic study (N=6) identifying usability and human-LLM interaction challenges. This motivated the design of Thinkink, with a final study (N=10) examining how people incorporate it into their ideation practices. We contribute design implications and a tool for ink-native LLM interaction where the user and LLM write and draw in a shared 2D canvas.