# AI Agentic Assistants that research and write papers with you

> You pick the problem and the benchmark. A team of AI Agentic Assistants reads the literature, proposes and tests ideas, checks every number, and writes the paper with you. You are the author and you decide what is submitted.

You pick the problem and the benchmark, so you lead the research. The Scientist assistant finds where the current best method falls short, ranks ideas, and designs the experiments. The Researcher reads the literature and keeps only references it found and checked. The Coder reproduces the baseline and runs each idea. The Copywriter turns the results into a paper in your voice. You are the author, and nothing is submitted, sent, or paid for without your go.

## How it works

1. **Set a goal.** You say what done looks like: a ticket, a client, a deadline, or a draft.
2. **The team works.** The assistants take the goal, use the ready prompts and skills, and do the work in the tools you connected.
3. **You approve the risky step.** Anything that sends, publishes, ships, or charges waits for your Approve. Approve a kind of step once and that assistant remembers it, but money always asks.
4. **You get the result.** Checked experiments and a LaTeX draft with its tables, references, and a short AI disclosure for you to edit, ready for your review.

## The team

- **You, the CEO.** You pick the problem and the benchmark, approve compute that costs money, and are the author who decides what is submitted.
- **Scientist assistant.** Leads the research. Finds the limits of the current best method, proposes and ranks ideas, designs the experiments and the ablations, and checks every number and claim against the results files.
- **Researcher (Scientist assistant).** The Scientist assistant in its research role: searches the literature in arXiv, OpenAlex, INSPIRE-HEP, and Europe PMC, and keeps only references it found and checked. A gap is marked as needing a source.
- **Machine learning engineer (Coder).** Reproduces the baseline, implements each idea, and runs pinned, seeded experiments on its own computer. A heavy training run goes on a GPU you control, and it starts after your Approve.
- **Academic writer (Copywriter).** Turns the results into a LaTeX paper, an abstract, and the reply to reviewers, in your voice. You edit, and nothing is submitted without your Approve.

## How the paper gets made

- **Numbers from the results files.** Tables and figures are made by scripts from the results the experiments saved, never typed from memory, so a number in the text can be traced to a file.
- **References that were found and checked.** A reference is listed only after the assistant found the paper and checked its title, authors, year, and identifier. A gap is marked as needing a source.
- **Reproducible code.** Experiments run with pinned versions and fixed seeds, and the scripts are kept next to the results, so anyone can run them again.
- **A reviewer's read before you submit.** Ask the Scientist assistant to read the draft as a reviewer would. It checks each claim against the results and lists the weak points and the experiments a reviewer would ask for.
- **A full research run on its own.** Coming soon.

## Integrations

- Science databases
- GitHub
- Hugging Face
- Google Drive
- Weights & Biases (MCP server)

## Ready prompts

- Reproduce the baseline of this paper from its repository on this benchmark, and tell me how close the numbers are to the published ones.
- List the limitations of the current best method on this benchmark, then propose three ideas and rank them by how much they might gain and how cheap they are to test.
- Run an ablation of each component of my method with three seeds, and show the results with intervals.
- Draft the paper in LaTeX with every table generated from the results files, and flag any claim the results do not support.
- Check every reference in this bibliography: does the paper exist, and do the title, authors, and year match?
- Find the closest prior work to this idea and tell me plainly if it has been done.
- Write the reply to reviewers and run the extra experiments they asked for, for my review.

## Skills

- Research brief
- Literature search
- Generate and verify
- Reproducible analysis
- Research paper in LaTeX
- Edit and proofread

## Questions

### Who is the author?

You are. The assistants are not authors. Journals and conferences ask you to disclose AI help, so the draft includes a short disclosure for you to edit.

### Does it invent results or citations?

No. A number comes from a results file, and a reference is listed only after it was found and checked. Anything it cannot support is marked as needing a source or a run.

### Where do the experiments run?

On the assistants' own computers. A big training run goes on a GPU you control, and it starts only after your Approve.

### What waits for my Approve?

Money, sending, publishing, and submitting. Approve a kind of step once and that assistant remembers it, but money always asks. Reading, analysis, and drafts run on their own.

### Which fields does it work in?

Machine learning is the first fit, since the experiments are code and a benchmark. The Scientist assistant also works in physics, mathematics, statistics, and the life sciences, where the literature and the analysis are the main work.

### Can I use it for graded coursework or a thesis?

It follows your university's rules on AI help, and it does not write graded work for a student to hand in as their own. Ask your supervisor what is allowed, and disclose the help you use.

### Is the full research run available?

Coming soon. It is the multi-day loop: ideas tested on a subset, the best ones scaled up, ablations, then review and rebuttal. Today you steer each stage.

### How do I start?

Sign up free, name the problem and the benchmark, and ask for the baseline first. The prompts and skills are ready.

## Related

- [Scientists](https://stellarfirm.ai/scientists)
- [Universities](https://stellarfirm.ai/universities)
- [Health research](https://stellarfirm.ai/health-research)
- [All starter templates](https://stellarfirm.ai/starter-templates)
- [Create your team](https://stellarfirm.ai/sign-up?redirect_url=%2Fapp%2Fstarter-templates%3Ftab%3Dcompanies%26setup%3Dresearch-lab)

---

Source: https://stellarfirm.ai/ai-research-papers
Markdown: https://stellarfirm.ai/ai-research-papers.md