Story2Proposal: A Scaffold for Structured Scientific Paper Writing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908918862577664 |
|---|---|
| author | Qian, Zhuoyang Shi, Wei Lin, Xu Ling, Li Luo, Meng Wang, Ziming Zhang, Zhiwei Xu, Tengyue Liu, Gaoge Zhang, Zhentao Zhang, Shuo Wang, Ziqi Feng, Zheng Luo, Yan Xu, Shu Chen, Yongjin Feng, Zhibo Chen, Zhuo Yuan, Bruce Wu, Biao Wang, Harry Chen, Kris |
| author_facet | Qian, Zhuoyang Shi, Wei Lin, Xu Ling, Li Luo, Meng Wang, Ziming Zhang, Zhiwei Xu, Tengyue Liu, Gaoge Zhang, Zhentao Zhang, Shuo Wang, Ziqi Feng, Zheng Luo, Yan Xu, Shu Chen, Yongjin Feng, Zhibo Chen, Zhuo Yuan, Bruce Wu, Biao Wang, Harry Chen, Kris |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27065 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Story2Proposal: A Scaffold for Structured Scientific Paper Writing Qian, Zhuoyang Shi, Wei Lin, Xu Ling, Li Luo, Meng Wang, Ziming Zhang, Zhiwei Xu, Tengyue Liu, Gaoge Zhang, Zhentao Zhang, Shuo Wang, Ziqi Feng, Zheng Luo, Yan Xu, Shu Chen, Yongjin Feng, Zhibo Chen, Zhuo Yuan, Bruce Wu, Biao Wang, Harry Chen, Kris Computation and Language F.2.2; I.2.7 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. |
| title | Story2Proposal: A Scaffold for Structured Scientific Paper Writing |
| topic | Computation and Language F.2.2; I.2.7 |
| url | https://arxiv.org/abs/2603.27065 |