ResearchStudio

Our AI co-author, from research problem to final publication.

ResearchStudio is a collection of skills covering the entire research lifecycle — from an under-specified research direction to a published paper. The skills run on Claude Code and Codex.

---

: one research paper, all deliverables (editable poster, video, blog, and reel)

📄 Paper  ·  💻 Code  ·  🎬 Demo

_{Presenting an all-in-one interactive reel.}

: one research direction, one reviewer-defensible idea card

📄 Paper  ·  💻 Code  ·  🎬 Demo

_{IdeaSpark runs the full pipeline end-to-end.}

News 🔥🔥🔥

• [2026-08-13] feature IdeaSpark hands a dead end to the next attempt — an abandoned candidate now carries what passing would take: the condition any mechanism there needs, what is ruled out, and what to salvage.
• [2026-08-13] fix IdeaSpark audit guards can no longer stall a run — the re-check loops are bounded, and findings no compliant audit cleared route into the normal retry instead of repeating forever.
• [2026-08-13] feature IdeaSpark keeps the whole user query — the user query is persisted verbatim and read by every phase that reasons about intent; papers named in it without a link are resolved and deep-read; and a stated solution direction reaches idea selection, which must record whether it followed or departed from that direction, and why.
• [2026-07-08] release ResearchStudio-Reel is released — the post-paper half: turn a finished paper PDF into the artifacts a publication needs — a print-ready poster, a narrated walkthrough video, a bilingual blog post, and an interactive reel viewer.
• [2026-07-03] release ResearchStudio-Idea is released — the pre-paper half: turn an under-specified research direction into a reviewer-defensible, implementable idea, grounded in an empirical taxonomy induced from a large-scale corpus of ICLR / ICML / NeurIPS submissions.

Quick Start

We recommend creating an isolated environment first, using either conda or uv:

Option 1 — conda:

conda create -n researchstudio "python>=3.10" -y
conda activate researchstudio

Option 2 — uv:

uv venv --python 3.10
source .venv/bin/activate  # Windows PowerShell: .venv\Scripts\Activate.ps1

Then pick one of the two install paths below:

Option 1 — clone and run install.sh (installs native tools, Python deps, symlinks the skills from a local clone and scaffolds .env):

git clone https://github.com/microsoft/ResearchStudio.git && cd ResearchStudio
bash install.sh

Option 2 — interactive npx installer (choose which plugins to install, enter your API keys when prompted, and it writes .env):

npx github:microsoft/ResearchStudio

For usage, see Idea and Reel. We recommend using these skills with model versions $\ge$ claude-opus-4.6 or gpt-5.5.

License

MIT

Citation

If ResearchStudio helps your research workflow, please cite:

@article{xiao2026researchstudioreel,
  title   = {ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog},
  author  = {Lingao Xiao and Yalun Dai and Yangyu Huang and Qihao Zhao and Wenshan Wu and Hugo He and Ruishuo Chen and Jin Jiang and Qianli Ma and Jiahuan Zhang and Xin Zhang and Ying Xin and Yang Ou and Yan Xia and Scarlett Li and Longbo Huang and Zhipeng Zhang and Yang He and Yap Kim Hui and Yan Lu},
  journal = {arXiv preprint arXiv:2607.04438},
  year    = {2026},
  url     = {https://arxiv.org/abs/2607.04438}
}

@article{zhao2026researchstudioidea,
  title   = {ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes},
  author  = {Qihao Zhao and Yangyu Huang and Yalun Dai and Lingao Xiao and Jianjun Gao and Xin Zhang and Wenshan Wu and Scarlett Li and Yang He and Yan Lu and Yap Kim Hui},
  journal = {arXiv preprint arXiv:2607.04439},
  year    = {2026},
  url     = {https://arxiv.org/abs/2607.04439}
}