# Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods

arXiv: https://arxiv.org/abs/2602.07040 · HTML: https://mlsanity.com/paper/2602.07040/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 5 of 5)

- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Learning to Discover at Test Time](https://mlsanity.com/paper/2601.16175/) (2026)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [ZAPBench: A Benchmark for Whole-Brain Activity Prediction in Zebrafish](https://mlsanity.com/paper/2503.02618/) (2025)
- [Forecasting Whole-Brain Neuronal Activity from Volumetric Video](https://mlsanity.com/paper/2503.00073/) (2025)

## Built on by (most cited first, 5 of 5)

- [Structured Scaling of AI Discovery Across Diverse Scientific Domains](https://mlsanity.com/paper/2604.19341/) (2026)
- [Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators](https://mlsanity.com/paper/2605.22343/) (2026)
- [Socratic agents for autonomous scientific discovery in high-dimensional physical systems](https://mlsanity.com/paper/2606.26722/) (2026)
- [Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch](https://mlsanity.com/paper/2607.27687/) (2026)
- [Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries](https://mlsanity.com/paper/2610.06269/) (2026)

## Abstract (arXiv)

We introduce Aster, an AI agent for autonomous scientific discovery capable of operating over 20 times faster than existing frameworks. Given a task, an initial program, and a script to evaluate the performance of the program, Aster iteratively improves the program, often leading to new state-of-the-art performances. Aster's significant reduction in the number of iterations required for novel discovery expands the domain of tractable problems to include tasks with long evaluation durations, such as multi-hour machine learning training runs. We applied Aster to problems in mathematics, GPU kernel engineering, biology, neuroscience, and language model training. More specifically: the Erdos minimum overlap problem, optimizing the TriMul kernel, a single-cell analysis denoising problem, training a neural activity prediction model to perform well on ZAPBench, and the NanoGPT Speedrun Competition. Aster attains SOTA results in every task, except for ZAPBench, where it matches the performance of the best human solution with less than 1/190th of the compute. Aster is accessible via a web interface and API at asterlab.ai.