LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting

2026-09-25

AI Summary

This study addresses the challenges of global logical inconsistency and insufficient technical fidelity encountered by large language models in drafting long-form patents. To overcome these limitations, we propose a hierarchical logic tree framework that eliminates the need for expert-preset outlines by leveraging retrieval-augmented generation (RAG) and evidence-guided recursion to construct technical nodes. Furthermore, a hybrid traversal algorithm is designed to map the logic tree onto patent sections, ensuring content coherence and structural balance. This approach enables controllable and automated generation of long structured documents with high token efficiency. Experimental results demonstrate that the proposed method significantly improves content quality and linguistic standardization, outperforming strong baseline models.

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.

Problem

• Long-form text generation
• Patent drafting
• Logical structuring
• Technical reasoning
• Retrieval-Augmented Generation

Innovation

• LogicTree-RAG
• Retrieval-Augmented Generation
• Hierarchical Logic Tree
• Patent Drafting
• Long-form Text Generation