ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

2026-07-05

AI Summary

This work addresses the limitations of existing methods that generate posters, videos, and blog posts from academic papers in isolation, often yielding outputs lacking editability and cross-format consistency. To overcome this, the authors propose a “last-mile” automation paradigm grounded in skill composition and hard-rendering gating, featuring a shared extractor, three editable generators, and an interactive integration layer. This architecture enables one-time information extraction from a source paper and simultaneous generation of factually consistent, round-trip editable multimodal outputs. By integrating Claude Code and Codex capabilities with layout-aware DOCX repair, narrative-aligned highlighting, and interactive HTML visualizations, the system achieves state-of-the-art performance on the Paper2Poster benchmark—surpassing both prior systems and leading large language models in 84%–93% of cases—and delivers, for the first time, a complete suite of editable, cross-media artifacts.

Abstract

Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact in isolation that each re-extract the paper from scratch, usually ship one-way renders the author cannot reopen in PowerPoint or Word, and gates quality on soft VLM-preference scores that plateau while load-bearing sections still read as empty. We argue this last mile is best built as a composition of skills: thin agent-readable contracts that share one upstream extractor and wrap deterministic primitives in a measured-fill loop whose exits are hard pass/fail render gates. We instantiate this as ResearchStudio-Reel, five Claude Code and Codex skills organized into one shared extractor (Paper2Assets), three editable generators (Paper2Poster, Paper2Video, Paper2Blog), and one interactive convergence layer (Paper2Reel). Paper2Assets extracts each paper once into a shared bundle that can be reused by every downstream skill; The three generators produce a print-ready poster, a synchronized talk video, and a bilingual blog that stay factually consistent and round-trip through PowerPoint or Word; Paper2Reel then binds all three into a self-contained HTML viewer whose section-level clicks jump the video, slides, captions, and blog to matching content. On the Paper2Poster benchmark, our posters lead every aesthetic and information sub-criterion against both prior automated systems and single-shot frontier LLMs, surpassing the authors' own on aesthetics under two held-out VLM judges and winning overall on 84% to 93% of papers; capability audits further show that, by uniquely pairing narration-aligned on-slide highlights with a bilingual blog gated by layout-aware DOCX repair, ResearchStudio-Reel is the only pipeline to ship all three editable artifacts. Project is available at https://aka.ms/ResearchStudio

Problem

• research dissemination
• last mile automation
• scientific communication
• multimodal artifacts
• editable outputs

Innovation

• research dissemination automation
• shared extraction pipeline
• editable multimodal generation
• hard render gating
• cross-modal synchronization