Guardado en:
Detalles Bibliográficos
Autores principales: Amin, Rifat Mehreen, Adatepe, Alperen, Fernandes, Daniela, Buschek, Daniel, Butz, Andreas
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.15848
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917499895808000
author Amin, Rifat Mehreen
Adatepe, Alperen
Fernandes, Daniela
Buschek, Daniel
Butz, Andreas
author_facet Amin, Rifat Mehreen
Adatepe, Alperen
Fernandes, Daniela
Buschek, Daniel
Butz, Andreas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15848
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas
Amin, Rifat Mehreen
Adatepe, Alperen
Fernandes, Daniela
Buschek, Daniel
Butz, Andreas
Human-Computer Interaction
Computation and Language
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.
title Conversations in Space: Structuring Non-Linear LLM Interactions on a Canvas
topic Human-Computer Interaction
Computation and Language
url https://arxiv.org/abs/2605.15848