LogicTree helps structure academic writing with AI assistance
LogicTree: Object-Oriented Writing for Structured Human-AI Academic Authoring
Human-Computer Interaction
Summary
Writing academic papers is complicated because ideas need to be organized clearly and linked logically. Current AI tools just handle text linearly, which makes it hard to keep writing well structured. The authors created LogicTree, a tool that treats parts of writing like objects you can move and fix easily, helping both writers and AI work together better. Their tests showed LogicTree helped people organize ideas, feel less tired, and write with better logic than other AI helpers.
What this means in practice
- •For academic writing teams: Enable academic authors to organize complex arguments using an AI tool that supports structured, object-based writing in Overleaf.
- •For technical content creators: Provide technical writers with a tool to manage and revise logically structured documents more efficiently through hierarchical AI support.
Authors
Jiajun Zhu, Xinyu Cheng, Wenshuo Zhang, Huamin Qu, Yanna Lin
Abstract
Academic writing is non-linear, iterative, and structure-driven, requiring authors to develop fragmented ideas into arguments with local coherence and global consistency. However, current AI-assisted tools primarily exchange linear prompts and free-form text, forcing authors to reconstruct generated logic and repeatedly verify its alignment with their structural intentions. We propose object-oriented writing (OOW), an OOD-inspired representation and interaction paradigm in which persistent writing objects serve as shared, manipulable referents for authors and AI. We instantiate OOW in LogicTree, an Overleaf-integrated prototype that combines a hierarchical object representation with a structure-grounded writing assistance module for author-initiated generation and issue-grounded revision and a structural logical review module for inspecting local coherence and global consistency. A within-subjects study (N=12) provides initial evidence that, in controlled academic writing tasks, LogicTree helps users structure ideas, reduces workload, and improves measured logical quality compared with a conversational baseline.