Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas

2026-05-15

AI Summary

This work addresses the limitations of traditional linear interfaces for large language model (LLM) conversations, which hinder multi-path exploration and sustained complex interactions. To overcome this, the authors propose CanvasConvo, a nonlinear interaction paradigm that structures dialogue as a branching tree embedded within a spatial canvas, enabling users to spawn hypothetical scenarios from any node and navigate multiple conversational threads in parallel. The system integrates spatial layout, timeline-based navigation, context-aware prompt management, and automatically generated semantic summaries and tags to preserve coherence while enhancing exploratory capabilities. A field study with 24 participants over 5–7 days demonstrates that CanvasConvo significantly supports exploratory workflows and fosters diverse patterns of interaction with LLMs.

Abstract

Conversational interfaces powered by large language models (LLMs) are widely used for ideation and analysis, yet their linear structure limits exploration of alternatives and management of long-running interactions. We present CanvasConvo, a conversational interface concept that transforms linear chat into a branching conversation tree embedded in a spatial canvas. CanvasConvo enables users to explore what-if scenarios by branching directly from conversational content, supporting parallel development of alternative directions. These branches are visualized on a canvas while remaining integrated with a familiar chat interface, allowing users to switch between linear and non-linear interaction. Features such as timeline-based navigation, automatic tagging and summarization, and context-aware controls (e.g., goals, reusable prompts) support structured interaction and continuity. We evaluated CanvasConvo in a 5-7 day field study with 24 participants. Our findings highlight how non-linear conversational structures support exploratory workflows and different interactions in LLM-based work.

Problem

• conversational interfaces
• large language models
• non-linear interaction
• exploratory workflows
• branching conversations

Innovation

• non-linear conversation
• branching dialogue
• spatial canvas
• LLM interaction
• exploratory workflow