ResearchStudio-Reel：自動化研究的最後一哩路——從論文到海報、影片與部落格

摘要

研究傳播——將論文轉化為海報、演講影片和部落格文章——仍然是一個需要手動處理的「最後一里路」。過去的自動化方法將每項產出視為獨立作業，各自從頭開始重新提取論文內容，通常產出單向渲染的結果，作者無法在PowerPoint或Word中重新開啟，而且品質受到軟性視覺語言模型（VLM）偏好評分的限制，這些評分在關鍵章節仍顯得空洞時便已停滯不前。我們認為，這最後一里路最適合以技能組合的方式建構：透過精簡的、可被AI代理讀取的合約，共享同一個上游提取器，並在一個可測量填充的迴圈中包裹確定性基本元件，其退出點是嚴格的「通過/失敗」渲染關卡。我們將此構想具體化為ResearchStudio-Reel：由五項Claude Code與Codex技能組成，組織為一個共享提取器（Paper2Assets）、三個可編輯生成器（Paper2Poster、Paper2Video、Paper2Blog），以及一個互動式收斂層（Paper2Reel）。Paper2Assets將每篇論文提取一次，產生一個可被所有下游技能重複使用的共享捆綁包；三個生成器分別產出可印刷的海報、同步的演講影片，以及中英雙語的部落格文章，內容保持一致且可透過PowerPoint或Word進行來回編輯；Paper2Reel則將三者整合為一個自包含的HTML檢視器，當使用者點擊某個章節時，會同步跳轉至影片、投影片、字幕和部落格的對應內容。在Paper2Poster基準測試中，我們的海報在每項美學與資訊子指標上，不僅優於先前的自動化系統，也勝過一次性生成的前沿大型語言模型（LLM）；在兩位獨立視覺語言模型評審的評估下，我們的海報甚至超越原作者自行設計的版本，在84%至93%的論文上獲得整體勝出。能力審查進一步顯示，由於獨特地將與敘述對齊的投影片重點標示，以及透過版面感知的DOCX修復機制所產生的雙語部落格相結合，ResearchStudio-Reel是唯一能同時產出三項可編輯成果的完整管線。專案網址：https://aka.ms/ResearchStudio

English

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