Story2Proposal: A Scaffold for Structured Scientific Paper Writing
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LEARN: A Story-Driven Layout-to-Image Generation Framework for STEM Instruction
LEARN is a layout-aware diffusion framework designed to generate pedagogically aligned illustrations for STEM education. It leverages a curated BookCover dataset that provides narrative layouts and structured visual cues…
Layout-to-Image GenerationKnowledge GraphsBuilding Agent Harnesses for Scientific Curation from Multimodal Sources
Scientific discovery workflows often depend on structured curation from the literature. This is difficult for current agents because the key evidence is scattered across long text, dense tables, and figures, and the fina…
MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
Recent advancements in AI agents have demonstrated their growing potential to drive and support scientific discovery. In this work, we introduce MLR-Bench, a comprehensive benchmark for evaluating AI agents on open-ended…
scientific discoveryKISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science
Process-based simulation models encode decades of scientific understanding across the Earth sciences, yet the communities most exposed to climate risk and resource scarcity are the least able to use them. Here, we introd…
Features have life history. And we should care
Features in language models have life history: they emerge, persist, and die during training, yet the importance of that history remains largely unexplored. We find evidence of a persistent representational backbone, whi…