Self-improving AI / The AI Scientist
The AI Scientist
“We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, describes its findings by writing a full scientific paper, and then runs a simulated review process for evaluation.”
The AI Scientist is one of the projects on the self-improving AI map. Below is what it changes about itself, whether the change lasts, and whether it improves the improver, each with the line from its own source.
Where it sits
Columns: what it changes, from the surface to the deepest change. Rows: whether the change outlasts the run. A number is how many projects sit in that square. See it on the 3D map
- What it changes
- Prompts, memory, context“Finally, The AI Scientist adds the completed ideas and reviewer feedback to its archive of scientific findings, and the process repeats.”
- Does the change last
- Gone when the run ends“At each iteration, we prompt the language model to generate an interesting new research direction conditional on the existing archive, which can include the numerical review scores from completed previous ideas.”
- Does it improve the improver
- does not improve how it improves“In the future, we aim to use our proposed discovery process to produce self-improving AI in a closed-loop system using open models.”
- Who sets the goals
- people set the aim, the system picks tasks“The AI Scientist is able to generate its own scientific ideas and hypotheses, as well as a plan for testing them with experiments.”
- How it was tested
- own benchmark numbers“We find that Sonnet 3.5 consistently produces the best papers, with a few of them even achieving a score that exceeds the threshold for acceptance at a standard machine learning conference from the Automated Paper Reviewer.”
The research it does is on ML problems in human-made templates: diffusion, NanoGPT and grokking. Inside the system, what grows is an archive of ideas and review scores that conditions the next ideas; in the experiments, ideas were generated without waiting for review scores to be added to the archive. Papers are scored by its own GPT-4o reviewer, which the authors checked against 500 ICLR 2022 papers. Research on its own code is listed as a future direction.
Does it count as RSI?
It depends on the definition. Under the four used on What counts as RSI, by what its own source says:
- Loose (Eliezer Yudkowsky, Intelligence Explosion Microeconomics (2013)): does not count
- Durable (Ren et al., self-improvement survey (2026)): does not count
- Strict (Roman Yampolskiy, From Seed AI to Technological Singularity (2015)): does not count
- Autonomous (Anthropic, When AI builds itself): does not count
How it got here
Earlier work in this catalog that The AI Scientist cites, oldest first. Under each: where that work sits on the map, then where The AI Scientist sits (changes in bold), and what The AI Scientist's own paper says about it. Its whole family on the citation map
2023 Reflexion uses it
Prompts, memory · gone when the run ends · does not improve the improver
“We use multiple rounds of chain-of-thought ([Wei et al., 2022](https://arxiv.org/html/2408.06292v1#bib.bib89)) and self-reflection ([Shinn et al., 2024](https://arxiv.org/html/2408.06292v1#bib.bib76)) to refine and develop each idea.”
2024 The AI Scientist
Prompts, memory · gone when the run ends · does not improve the improver
Cited by ADAS 2024, Gödel Agent 2024, Darwin Gödel Machine 2025, PostTrainBench 2026, Hyperagents 2026, Ren, self-improvement 2026, AREX-2 2026, LM2LM 2026, Organon 2026, RSI Arena 2026, AutoTavern 2026, ParetoRSI-Gym 2026, Infinity Machine 2026
In the same square
ADAS: Automated Design of Agentic Systems, AlphaEvolve, AREX-2, LM2LM, MLEvolve, ParetoRSI-Gym, PostTrainBench, Promptbreeder, Reflexion, Self-Refine