Scholarlink

<p>Academic paper writing is a time-consuming and demanding component of the scientific research workflow. Although large language models (LLMs) have achieved remarkable advances in text generation, single-turn direct generation strategies face critical challenges when applied to long-form, multi-section academic papers, including incomplete sections, content truncation, formatting irregularities, and reference hallucinations. We propose PaperOrchestrator, an LLM-orchestrated multi-agent pipeline system that decomposes automatic academic paper writing into seven collaborative stages: outline generation, section-by-section content generation, length-adaptive control, full-text consistency polishing, BibTeX reference generation, section-by-section robust LaTeX conversion, and journal template rendering, with inter-stage information transfer and state management achieved through a shared context data structure. On an evaluation set of 60 papers spanning natural language processing, computer vision, and biomedical AI, we compare against 11 baseline systems including GPT-4o, GPT-4-Turbo, Gemini&#xa0;1.5&#xa0;Pro, Claude&#xa0;3.5&#xa0;Sonnet (single-turn), Llama-3.1-70B, Qwen2.5-72B, and ChatPaper. PaperOrchestrator achieves state-of-the-art performance on BERTScore F1 (0.674), ROUGE-L (0.223), section completeness (96.7%), LaTeX compilation rate (90.0%), and human-evaluated overall quality (3.85/5.00, Krippendorff’s <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\alpha =0.73\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>α</mi> <mo>=</mo> <mn>0.73</mn> </mrow> </math></EquationSource> </InlineEquation>), with all differences reaching statistical significance after Bonferroni correction. Ablation experiments validate the necessity of core components including the Continue Mechanism and the Section-by-Section LaTeX Conversion strategy. This work provides a reproducible, systematic framework and a comprehensive empirical benchmark for LLM-driven automated academic writing.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PaperOrchestrator: An LLM-Orchestrated multi-agent pipeline for automated end-to-end scientific paper writing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月6日

查看全文
  • Chunhong Yuan,
  • Tianshi Wei,
  • Chuangqi Li,
  • Xing Yi,
  • Shengrui Liu,
  • Zixin Zhang,
  • Yule Cai,
  • Xinke Du

摘要

Academic paper writing is a time-consuming and demanding component of the scientific research workflow. Although large language models (LLMs) have achieved remarkable advances in text generation, single-turn direct generation strategies face critical challenges when applied to long-form, multi-section academic papers, including incomplete sections, content truncation, formatting irregularities, and reference hallucinations. We propose PaperOrchestrator, an LLM-orchestrated multi-agent pipeline system that decomposes automatic academic paper writing into seven collaborative stages: outline generation, section-by-section content generation, length-adaptive control, full-text consistency polishing, BibTeX reference generation, section-by-section robust LaTeX conversion, and journal template rendering, with inter-stage information transfer and state management achieved through a shared context data structure. On an evaluation set of 60 papers spanning natural language processing, computer vision, and biomedical AI, we compare against 11 baseline systems including GPT-4o, GPT-4-Turbo, Gemini 1.5 Pro, Claude 3.5 Sonnet (single-turn), Llama-3.1-70B, Qwen2.5-72B, and ChatPaper. PaperOrchestrator achieves state-of-the-art performance on BERTScore F1 (0.674), ROUGE-L (0.223), section completeness (96.7%), LaTeX compilation rate (90.0%), and human-evaluated overall quality (3.85/5.00, Krippendorff’s \(\alpha =0.73\) α = 0.73 ), with all differences reaching statistical significance after Bonferroni correction. Ablation experiments validate the necessity of core components including the Continue Mechanism and the Section-by-Section LaTeX Conversion strategy. This work provides a reproducible, systematic framework and a comprehensive empirical benchmark for LLM-driven automated academic writing.