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

TL;DR

This paper introduces CanvasConvo, a spatial, non-linear conversational interface for large language models that enhances exploration and management of complex, branching interactions.

Contribution

The paper presents CanvasConvo, a novel spatial interface that transforms linear chats into interactive, visualized branching conversation trees for improved exploration.

Findings

Non-linear structures support exploratory workflows.

Users can manage multiple conversation branches effectively.

The interface enhances interaction flexibility and continuity.

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.