用契约机制让多个AI协作写论文，避免内容错乱。
Story2Proposal: A Scaffold for Structured Scientific Paper Writing
- 用共享契约管理各AI角色，确保结构与图表一致
- 在4个主流模型上比直接生成高2.182分（专家评分）
- 适合需要严谨结构的科研写作，如投稿或项目书
生成科学论文需保持叙事逻辑、实验证据与视觉元素在整个文档生命周期中的一致性。现有语言模型生成流程依赖无约束文本合成，仅在生成后验证，常导致结构偏移、图表缺失和跨章节不一致。我们提出Story2Proposal，一种基于契约的多智能体框架，通过协同代理在持久共享视觉契约下将研究故事转化为结构化论文。系统围绕契约状态组织架构师、写作者、优化者和渲染者代理，评估代理在生成-评估-适应循环中提供反馈并更新契约。在源自Jericho研究语料的任务上，Story2Proposal在GPT、Claude、Gemini和Qwen等模型上获得6.145分（专家评分），显著高于DirectChat的3.963分（+2.182）。相较于结构化生成基线Fars，平均得分5.705优于5.197，表明其结构一致性与视觉对齐能力提升。
原文摘要 · Abstract (English)
Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。