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

arXiv:2609.30943 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Comments: Accepted by NeurIPS 2026

Code: https://github.com/boschresearch/Pap2Pat

License: http://creativecommons.org/licenses/by/4.0/

The gist: 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

Terminology

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.

Sources

Related papers