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

Jiaqi Zhu; Naili Xing; Hexiang Pan; Haotian Gao; Jianwei Yin; Xiaokui Xiao; Beng Chin Ooi

cs.AISep 25, 2026

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

Authors: Jiaqi Zhu, Naili Xing, Hexiang Pan, Haotian Gao, Jianwei Yin, Xiaokui Xiao, Beng Chin Ooi

Organizations: National University of Singapore · Zhejiang University

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.

Figures & tables

Figure 1: Architecture of LogicTree-RAG framework for long-form patent drafting.

Figure 2: Generation without and with node-aware semantic search.

Panel of Table 1 — Table 1: Overall performance comparison of long-form patent drafting. The best results are highlighted in bold , and the second-best results are in bold .

Figure 5: Section-level performance in terms of output length, content coverage, and linguistic style.

Figure 7: Hyperparameter Sensitivity Analysis.

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Notation	Description
$(X,P)$	A patent-paper pair, where $X$ is the source (pre-publication) research paper and $P$ is the corresponding patent document.
$X=\{x_{1},x_{2},\dots,x_{m}\}$	Source paper represented as a collection of $m$ text spans.
$P=\{p_{1},\dots,p_{n}\}$	Patent document represented as a collection of $n$ text spans.
$\tilde{X}=\{\tilde{x}_{1},\tilde{x}_{2},\dots,\tilde{x}_{L}\}$	Semantic chunks produced from $X$ after layout-aware semantic chunking, with $L\leq m$ .
$\mathcal{T}=(V,E,r)$	Logic tree, a directed rooted tree with node set $V$ , edge set $E\subseteq V\times V$ , and root node $r$ .
$V=\{v_{1},\cdots,v_{N}\}$	Set of logic tree nodes, each representing a technical element (e.g., principle, step, subsystem).

Appendix

Table 3: Notations.

Method	Output Tokens	Content-level				Language-level			Time (s) / Patent (Token)
		Coverage $\uparrow$	Factuality $\uparrow$		Semantic Similarity $\uparrow\,\,$	Style $\uparrow$	Repetition Rate $\mathcal{R}_{r}$ $\downarrow$	Coherence $\uparrow$
		Coverage $\uparrow$	$\mathcal{F}_{Pat}$	$\mathcal{F}_{Src}$	Semantic Similarity $\uparrow\,\,$	Style $\uparrow$	Repetition Rate $\mathcal{R}_{r}$ $\downarrow$	Coherence $\uparrow$
Heuristic Skyline
Reference Patent (GT)	18.16k	89.05	88.74	88.80	100	100	13.91	100	-
Source Paper	8.03k	44.77	46.06	88.68	39.37	39.26	8.39	98.60	-
Outline (Long)	1.43k	39.11	61.79	61.93	10.16	23.22	20.14	85.69	-

Appendix

Table 4: Performance of LogicTree-RAG with different backbone LLMs.

Panel of Table 5 — Table 5: Performance comparison of LogicTree-RAG against agentic baselines for patent drafting.

Method	Fully (%)	Partial (%)	Unsupported (%)
LLM-as-judge
COPGEN	70.4	20.2	9.4
LogicTree-RAG	85.6	12.0	2.4
Human Audit
COPGEN	60	30	10
LogicTree-RAG	75	25	0

Appendix

Table 6: Evidence-support analysis of retrieved evidence and generated content.

Computational Cost (/patent)	Cost Breakdown
LLM Calls: 20	chunking&tree init 5%, tree construction 45%, traversal 50%
Runtime: 311s	chunking&tree init 16%, tree construction 39%, traversal 45%
Total Input Tokens: 7.60k	chunking&tree init 29%, tree construction 37%, traversal 34%

Appendix

Table 7: Supplementary computational cost analysis.

Method	Overall	Legality	Claim Structure	Antecedent Basis	Fidelity
Ours vs Qwen3-80B	75.7	69.8	84.6	84.8	88.5
Ours vs DeepseekV3	84.4	65.1	88.5	90.1	90.2
Ours vs LongWriter	78.8	76.5	90.6	92.0	85.9
Ours vs COPGEN	70.5	65.7	85.2	82.1	78.5

Appendix

Table 8: Win-rate results of LogicTree-RAG in human expert evaluation.

Figure 8: Sensitivity to tree growth budget in LogicTree-RAG.

Figure 9: Qualitative case study illustrating a patent example generated by LogicTree-RAG.

Figure 10: Qualitative case study illustrating the ground-truth reference patent.

Long-Form Document Generation

Long-form document generation studies methods for producing coherent, factual, well-structured books, reports, and other extended texts with AI.

See all 32 papers

Benchmarking Patent Drafting from Inventor-Style Disclosures
Aug 21, 2026Lekang Jiang, Wenjun Sun, Stephan GoetzLanguage Model Generation Evaluation
University of Cambridge · National Science Library, Chinese Academy of Sciences · Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences
Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching
Aug 11, 2026Jian Zhang, Songlin Lei, Zhuohao Yang +6Retrieval-Augmented Generation Information Retrieval
School of Computer Science and Technology, Zhejiang University, Hangzhou, China · ZJU-UIUC Institute, Zhejiang University, Haining, China · Shaoxing K3i Technology Co. Ltd +1
When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation
Jul 11, 2026Lekang Jiang, Wenjun Sun, Stephan GoetzLLM Prompting CoT Reasoning
University of Cambridge · National Science Library, Chinese Academy of Sciences; Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences.

Aug 21, 2026J/K move · Enter open · S save

Benchmarking Patent Drafting from Inventor-Style Disclosures

Lekang Jiang, Wenjun Sun, Stephan Goetz

University of Cambridge · National Science Library, Chinese Academy of Sciences · Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences

Language Model Generation Evaluation

Open paper AskPDF arXiv

While recent large language models (LLMs) have achieved promising results on individual patent drafting tasks, they fundamentally fail to investigate the core challenge of real-world patent drafting: generating a complete and legally coherent patent application directly from early-stage invention materials. Prior work predominantly assumes later-stage, highly structured, or already legalistic inputs. However, real patenting workflows begin with informal, de-legalized disclosures authored by inventors. To bridge the gap, we introduce Dis2Pat, a disclosure-to-patent dataset that reflects realistic patenting workflows by requiring the generation of complete patent applications directly from inventor-style, de-legalized disclosures. Given the inherent difficulty of long-form, legally constrained patent drafting and the strong privacy requirements, we further propose a strong baseline named Patent-MAF. It is a multi-agent framework for locally deployable patent drafting. Benchmark results reveal that current LLMs exhibit limitations in patent drafting, while Patent-MAF provides a strong baseline that consistently outperforms evaluated open-source models and remains competitive with large closed-source models.

Abstract

Long-Form Document Generation

Explore similar work

Benchmarking Patent Drafting from Inventor-Style Disclosures

Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching

When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation