TombWriter: Scaffolding Story Archeology through Beat-Level Interaction in Human-AI Co-Writing

2026-05-19

AI Summary

This work proposes a novel LLM-based collaborative writing approach grounded in “story archaeology,” addressing limitations of conventional AI-assisted writing that relies on one-off prompts, often yielding imprecise outputs, cumbersome workflows, and diminished authorial agency and ownership. The method innovatively structures narratives hierarchically using beats as fundamental units, decoupling story logic from textual style. A five-stage LLM-driven narrative pipeline supports iterative management of characters, settings, and beats through an interactive visual card interface, ultimately generating stylized prose. In a three-day qualitative study with five experienced writers, participants regarded the AI as a generative engine for structural exploration and strongly affirmed its support for creative control, despite concerns about voice erosion, underscoring the approach’s value in enhancing narrative agency and authorship.

Abstract

The dominant paradigm for LLM interaction in AI co-writing uses disposable prompts that vanish after use. This may lead to imprecise results, cumbersome workflows, and diminished author agency and ownership. We propose LLM-based story archeology, where prompts serve as a hierarchical story instrument refined over time to extract the writer's intended story. Drawing on the fossil theory of story- telling, where stories exist as latent structures that writers excavate through their craft, this approach supports agency and ownership through high involvement and control. Writers work at the level of story beats rather than prose. They generate character actions in scenes to discover emergent possibilities, simulated by the LLM or directly nudged, then edit resulting beats to refine scenes iteratively. Prose is generated from beats based on style and genre, separating structure from style. We developed TombWriter, a web-based tool that visualizes stories as navigable cards -- characters, scenes, and beats -- through a five-stage narrative pipeline. We conducted a qual- itative study with five experienced writers who used the system over three days. Through semi-structured interviews, we found that writers framed AI as a generation engine rather than collabo- rator, claimed ownership while reporting voice loss, and valued the system for structural discovery rather than prose production. We contribute the story archeology approach, the TombWriter system, and qualitative findings on beat-level human-AI co-writing.

Problem

• AI co-writing
• LLM interaction
• author agency
• prompt disposability
• story structure

Innovation

• story archaeology
• beat-level interaction
• human-AI co-writing
• hierarchical prompting
• structure-style separation