CoAuthorAI: A Human in the Loop System For Scientific Book Writing

TL;DR

CoAuthorAI is a human-in-the-loop system that enhances scientific book writing by combining retrieval-augmented generation, hierarchical outlines, and expert refinement, significantly improving coherence and reliability.

Contribution

It introduces a novel collaborative system integrating LLMs with expert input for full-length scientific books, addressing LLM limitations in structure and citations.

Findings

Achieved 98% soft-heading recall in literature review chapters

Reached 82% satisfaction rate in human evaluation of generated articles

Enabled publication of a scientific book using CoAuthorAI and LUFFA AI

Abstract

Large language models (LLMs) are increasingly used in scientific writing but struggle with book-length tasks, often producing inconsistent structure and unreliable citations. We introduce CoAuthorAI, a human-in-the-loop writing system that combines retrieval-augmented generation, expert-designed hierarchical outlines, and automatic reference linking. The system allows experts to iteratively refine text at the sentence level, ensuring coherence and accuracy. In evaluations of 500 multi-domain literature review chapters, CoAuthorAI achieved a maximum soft-heading recall of 98%; in a human evaluation of 100 articles, the generated content reached a satisfaction rate of 82%. The book AI for Rock Dynamics generated with CoAuthorAI and Kexin Technology's LUFFA AI model has been published with Springer Nature. These results show that systematic human-AI collaboration can extend LLMs' capabilities from articles to full-length books, enabling faster and more reliable scientific publishing.