Story2Proposal：结构化科研论文写作框架

摘要

生成科學文稿需在文件生命週期中保持敘事邏輯、實驗證據與視覺元素之間的協調一致。現有基於語言模型的生成流程依賴無約束文本合成，且僅在生成後進行驗證，常導致結構漂移、圖表缺失及跨章節不一致等問題。本文提出Story2Proposal框架，採用契約治理的多智能體架構，通過在持久化共享視覺契約下協作的智能體，將研究故事轉化為結構化手稿。該系統圍繞追蹤章節結構與註冊視覺元素的契約狀態，組織架構師、撰寫者、優化者和渲染器四類智能體協同工作，同時由評估智能體在"生成-評估-適應"循環中提供反饋，動態更新生成過程中的契約。基於Jericho研究數據集的實驗表明，在GPT、Claude、Gemini和Qwen等多種模型基座上，Story2Proposal的專家評分達6.145分，顯著高於DirectChat的3.963分（提升2.182分）。與結構化生成基準Fars相比，Story2Proposal平均得分5.705分優於後者的5.197分，體現出更優的結構一致性與視覺元素協調性。

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.

Story2Proposal：结构化科研论文写作框架

Story2Proposal: A Scaffold for Structured Scientific Paper Writing

摘要

Support