To speed up research, we have to shorten
the loop from idea to feedback.
That lets us test more ideas, learn faster, and push the frontier along the way. Agents will be at the core of that process, performing the gruntwork, guided by the scientist’s hand. rapidreview is building systems to make this approach to AI research easier.
The atomic unit of scientific research is testing a novel idea and learning from the outcome. Repeated, it accumulates knowledge and leads to better ideas, pushing the frontier of understanding and performance. Everything else in a lab exists to serve that test.
The shorter the loop from idea to feedback, the faster we iterate. The group with the tighter loop asks better questions, because every answer arrives while the question is still fresh.
Agents change both halves of the loop: a raw idea gets polished against previous research and experiments, and execution is automated to preserve the scientist’s focus. Better experiments and faster execution compound into more signal to learn from — and every run leaves reliable data behind for the runs that follow. The figure above is our whole argument. Everything we build lives somewhere on it.
Novel ideas are the prerequisite for any significant advance in research. They arise from human ingenuity — in creative ideation, we will hold an edge over AI models for the foreseeable future. Relevant evidence is required to sharpen an idea or kill it before allocating resources. Retrieving that evidence is a search and reasoning task — the type of work agents do well, and one they can do at scale.
So that is what we build. A living map of research — every dot a paper, edges shared ideas or citations. Indexed for agent swarms to search, visualized for humans to understand. Its search and recommendation engine hands every new experiment the right prior research. Most wasted compute is an experiment that needed a better design; better designs start by consulting what the field already knows.
Agents excel at completing well-defined tasks with set evaluations; engineering-dominant fields such as AI research are well suited for their use. Working with agents raises two significant challenges: reliability and visibility. Advanced models are known to pursue the shortest path to success by cheating the process, or quietly adjusting the goal to reach it in fewer steps. When agents execute in parallel, this compounds into a visibility problem for the scientist: results are easier to trust when you can see how they were reached, and the decisions made along the way carry lessons worth surfacing.
Agents run the experiments. People interpret the results.
Our approach to agentic execution centers on gating mechanisms: independent adversarial reviews injected at key moments, and machine-verifiable artifacts required throughout the run. The artifacts power the user interface, whose job is to tell the story of the experiment: what was tried, what was decided, and why, so scientists can understand the agents’ work. With every run gated and decisions visible, delegating parallel experiments to agents becomes a viable approach to research, letting scientists test more ideas and learn faster.
The right hardware is whatever you can reach right now: a Lambda cluster, a single cloud GPU, the university machine, or the laptop on your desk. Experiments are sized to the hardware at hand, from a $1 smoke test to a $10,000 sweep.
Because a round now spans many machines at once, monitoring is part of the instrument — watching progress across a fleet by hand is the definition of intractable.
We ship the framework as two instruments. Maps is the ideation half: a living map of 500,000+ ML papers and the twenty million connections between them — semantic search, similar-work neighborhoods, and a research agent that reads the field with you. It is live today in early access, with a public API, a Python SDK, and docs.
Merv is the execution half, built against the two things agents still lack: reliability and visibility. Models get better at the task every month, so Merv is not another agent harness — it is the gating mechanism around whichever agent you run: project state, resources, and independent design and experiment reviews, with cloud sandboxes for the runs. It is open source and installs into the coding agents you already use.
Both are in daily use on our own research.
If you are passionate about solving inefficiencies in AI research, we should talk.