Story2Proposal: A Scaffold for Structured Scientific Paper Writing

2026-03-27

AI Summary

This work addresses the challenges of structural inconsistency, missing content, and cross-section incoherence commonly encountered in automatically generated scientific papers, particularly between narrative text, experimental evidence, and visual elements. To resolve these issues, the authors propose a multi-agent collaborative framework grounded in a persistent shared visual contract, comprising architect, writer, optimizer, renderer, and evaluator agents. These agents operate within a generate–evaluate–adapt loop that dynamically updates the contract to align textual structure with visual components throughout the document. The approach introduces, for the first time, a contract-driven mechanism to regulate multi-agent collaboration. Evaluated on the Jericho corpus, the method achieves an expert rating of 6.145, significantly outperforming DirectChat (3.963) and Fars (5.197), thereby demonstrating substantial improvements in both structural coherence and text–figure consistency.

Abstract

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.

Problem

• scientific manuscript generation
• structural consistency
• visual alignment
• narrative reasoning
• cross-section inconsistency

Innovation

• multi-agent framework
• visual contract
• structured generation
• scientific writing
• generate-evaluate-adapt loop