Logic tree guided system improves patent drafting with large language models
LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
Artificial Intelligence
Summary
Writing long, complex technical documents like patents is hard because they must be organized logically and use detailed, accurate reasoning throughout. The authors created a new system called LogicTree-RAG that builds a structured 'logic tree' to organize ideas and guide the writing process automatically. This helps generate longer, well-organized patent drafts without needing experts to create outlines beforehand. Their tests showed this method produces higher-quality, more consistent technical writing than other large language model approaches.
What this means in practice
- •For patent professionals: Automate creation of comprehensive patent drafts by structuring and grounding technical content in a logical tree without manual outlines.
- •For technical writing teams: Generate longer, coherent technical documents efficiently by using logic tree guidance to maintain global consistency and detail.
Authors
Jiaqi Zhu, Naili Xing, Hexiang Pan, Haotian Gao, Jianwei Yin, Xiaokui Xiao, Beng Chin Ooi
Abstract
Long-form technical text generation underpins knowledge-intensive workflows, yet remains challenging for large language models (LLMs) due to the need for globally consistent logical structuring and faithful technical reasoning beyond local coherence. Patent drafting is a canonical instance of this challenge, demanding holistic generation of a legally compliant and technically exhaustive document through sustained multi-expert collaboration. Existing approaches often focus on partial section generation or rely on manually crafted outlines, limiting scalable automation in realistic settings. In this work, we propose LogicTree-RAG, a logic tree-guided retrieval-augmented generation framework that induces a hierarchical logic tree as a global organizational backbone to organize and ground technical disclosures, without relying on expert-defined drafting priors. Each node in the logic tree represents a technical element and is constructed through evidence-guided recursive generation. A hybrid traversal mechanism then maps the logic tree into patent sections, enabling controllable and section-balanced generation. Extensive experiments show that LogicTree-RAG consistently improves content quality and language conformity over strong LLM-based baselines and achieves longer structured generation with high token efficiency, demonstrating the effectiveness of logic-centric generation for complex technical document drafting.