Prompt-to-Paper：面向生物信息学的智能体 AI 系统
英文标题：Prompt-to-Paper: Agentic AI System for Bioinformatics
大型语言模型虽能端到端生成论文，但现有系统存在三大缺陷：声明缺乏可验证文献支撑、实验结果常为虚构、缺乏标准化多维度评估框架。Prompt-to-Paper 多智能体框架通过确定性检索增强生成、自主编码执行真实实验以及八维质量评分器来解决这些问题，并用质量驱动的迭代改进循环持续优化输出。在五个生物信息学案例中，所有生成稿件引用零偏差，质量评分平均提升 17.96 分（百分制），人工评分为 7.0/10，每篇成本约 0.31 美元。该系统为可复现、高标准的 AI 科学写作提供了评估范式与改进机制。
2.6 KB
2.1 KB
640 B
612 B
380 B
9.1 KB
22.8 KB
24.2 KB
34.7 KB
中文
[提交于 2026年7月5日]
标题：Prompt-to-Paper：面向生物信息学的智能体 AI 系统
查看题为《Prompt-to-Paper: Agentic AI System for Bioinformatics》的论文 PDF，作者：Ramsha Kamran 等 5 人
摘要：尽管大语言模型的最新进展已使端到端的自动论文生成成为可能，但现有系统仍存在三个关键缺陷：(i) 生成的声明无法确定性地建立在可验证的文献之上，(ii) 实验结果常常是捏造的而非真实执行所得，(iii) 缺乏标准化的多维框架来评估 AI 生成的论文是否达到实际发表所需的质量与严谨性。我们提出 Prompt-to-Paper，一个通过三项集成创新直接填补这一评估鸿沟的多智能体框架。首先，一个具备章节感知相关性评分和滚雪球式引文扩展的确定性检索增强生成流水线，将每一条声明扎根于 60–100 篇可验证论文的语料库中。其次，一个自主编码智能体执行真实的计算生物学实验，用真实的数值结果替代合成输出。第三，一个八维自动质量评分器，以已发表论文的近似参考统计量为基准，并辅以明确的幻觉惩罚，提供标准化、可复现的质量评估。质量驱动的改进循环使用一个上下文丰富的修订器，将每次迭代路由到三种研究者动作之一，并每十次迭代触发一次深度研究循环，以重新运行实验并从更强的输出重新撰写论文。我们在五个生物信息学案例上验证了该系统；所有五个案例均编译出符合投稿格式的 PDF，且零引文超出范围。改进循环将论文质量在 0–100 分制上平均提升 +17.96 分（最高 +26.04 分）。作为部分外部检查，人类评审员对五篇论文的平均评分为 7.0 分（满分 10 分）。每篇完整论文的生成成本约 0.31 美元。
提交历史
来自：Muhammad Usman Shahid Khan Khan [ 查看邮箱 ]
[v1]
2026年7月5日，星期日 21:30:24 UTC (68,454 KB)
English / 原文
[Submitted on 5 Jul 2026]
Title:Prompt-to-Paper: Agentic AI System for Bioinformatics
View a PDF of the paper titled Prompt-to-Paper: Agentic AI System for Bioinformatics, by Ramsha Kamran and 5 other authors
Abstract:While recent advances in large language models have enabled end-to-end automated manuscript generation, existing systems suffer from three critical deficiencies: (i) generated claims are not deterministically grounded in verifiable literature, (ii) experimental results are frequently fabricated rather than executed, and (iii) there exists no standardized, multi-dimensional framework to assess whether AI-generated manuscripts meet the quality and rigor required for real-world publication. We present Prompt-to-Paper, a multi-agent framework that directly addresses this evaluation gap through three integrated innovations. First, a deterministic retrieval-augmented generation pipeline with section-aware relevance scoring and snowball citation expansion grounds every claim in a verifiable corpus of 60--100 papers. Second, an autonomous coding agent executes real computational biology experiments replacing synthetic outputs with genuine numerical results. Third, an eight-dimensional automated quality scorer, benchmarked with approximate reference statistics from published papers and augmented with explicit hallucination penalties, provides standardized, reproducible quality assessments. The quality-driven improvement loop uses a context-rich reviser that routes each iteration to one of three researcher actions and fires a deep research cycle every ten iterations to re-run experiments and re-manuscript from stronger outputs. We validate the system on five bioinformatics case studies; all five cases compiled submission-formatted PDFs with zero out-of-range citations. The improvement loop raises manuscript quality by an average of +17.96 points on a 0--100 scale (maximum +26.04. As partial external checks, a human reviewer scored the five manuscripts at an average of 7.0 out of 10. Complete manuscripts are produced at approximately 0.31 USD per paper.
Submission history
From: Muhammad Usman Shahid Khan Khan [
]
[v1]
Sun, 5 Jul 2026 21:30:24 UTC (68,454 KB)