atlas

Research map / Large language models / Agents, code and math

NarrativePlay: An Automated System for Crafting Visual Worlds in Novels for Role-Playing

AAAI 2024 · Large language models › Agents, code and math · approach: LLM-driven embodied and driving agents · 4 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Presents NarrativePlay, a web demo that extracts a novel's main storyline events and characters with an LLM and turns them into an interactive role-play experience with generated scene images, portraits and speech.

Problem

Role-playing agents in narratives usually rely on handcrafted sandboxes and manual character/environment settings, which are labour-intensive and not generalisable to new stories.

Approach

Automatically extract character traits and main storyline events from a narrative with an LLM, let the user pick a character, and generate event-specific environment visuals, character portraits and speech so the user experiences the story from that character's perspective.

Key results

Limitations

Experimental setup

Datasets: user-provided narratives (novels)

Builds on: Generative Agents

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy