# An AI system to help scientists write expert-level empirical software

arXiv: https://arxiv.org/abs/2509.06503 · HTML: https://mlsanity.com/paper/2509.06503/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2025.

## Built on by (most cited first, 30 of 60)

- [DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively](https://mlsanity.com/paper/2509.26603/) (2025)
- [KL-Regularized Reinforcement Learning is Designed to Mode Collapse](https://mlsanity.com/paper/2510.20817/) (2025)
- [Glia: A Human-Inspired AI for Automated Systems Design and Optimization](https://mlsanity.com/paper/2510.27176/) (2025)
- [AgenticSciML: Collaborative Multi-Agent Systems for Emergent Discovery in Scientific Machine Learning](https://mlsanity.com/paper/2511.07262/) (2025)
- [Sherlock: Reliable and Efficient Agentic Workflow Execution](https://mlsanity.com/paper/2511.00330/) (2025)
- [AlphaResearch: Accelerating New Algorithm Discovery with Language Models](https://mlsanity.com/paper/2511.08522/) (2025)
- [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026)
- [Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models](https://mlsanity.com/paper/2604.02485/) (2026)
- [Solving an Open Problem in Theoretical Physics using AI-Assisted Discovery](https://mlsanity.com/paper/2603.04735/) (2026)
- [ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms](https://mlsanity.com/paper/2512.03476/) (2025)
- [Improving Coherence and Persistence in Agentic AI for System Optimization](https://mlsanity.com/paper/2603.21321/) (2026)
- [Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models](https://mlsanity.com/paper/2608.09696/) (2026)
- [Towards a General Intelligence and Interface for Wearable Health Data](https://mlsanity.com/paper/2605.22759/) (2026)
- [Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods](https://mlsanity.com/paper/2602.07040/) (2026)
- [TusoAI: Agentic Optimization for Scientific Methods](https://mlsanity.com/paper/2509.23986/) (2025)
- [Engineering.ai: A Platform for Teams of AI Engineers in Computational Design](https://mlsanity.com/paper/2511.00122/) (2025)
- [ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research](https://mlsanity.com/paper/2605.28282/) (2026)
- [Generalizing PDE Emulation with Equation-Aware Neural Operators](https://mlsanity.com/paper/2511.09729/) (2025)
- [Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning](https://mlsanity.com/paper/2606.03962/) (2026)
- [Towards Autonomous and Auditable Medical Imaging Model Development](https://mlsanity.com/paper/2607.10522/) (2026)
- [Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies](https://mlsanity.com/paper/2608.12679/) (2026)
- [Accelerating Scientific Research with Gemini in the Real-World](https://mlsanity.com/paper/2608.26701/) (2026)
- [Workflow Closure Is Not Scientific Closure in Auto-Research Systems](https://mlsanity.com/paper/2605.26200/) (2026)
- [A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline](https://mlsanity.com/paper/2606.07718/) (2026)
- [Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems](https://mlsanity.com/paper/2607.09025/) (2026)
- [DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal data](https://mlsanity.com/paper/2608.05375/) (2026)
- [CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows](https://mlsanity.com/paper/2608.06961/) (2026)
- [Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods](https://mlsanity.com/paper/2608.08958/) (2026)
- [Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings](https://mlsanity.com/paper/2608.26088/) (2026)
- [Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish](https://mlsanity.com/paper/2602.04492/) (2026)

## Abstract (arXiv)

The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experimentscitehannay2009how. To address this, we present Empirical Research Assistance (ERA), an AI system that creates expert-level scientific software whose goal is to maximize a quality metric. The system uses a Large Language Model (LLM) and Tree Search (TS)citesilver2016mastering to systematically improve the quality metric and intelligently navigate the large space of possible solutions. ERA achieves expert-level results when it explores and integrates complex research ideas from external sources. The effectiveness of tree search is demonstrated across a diverse range of tasks. In bioinformatics, ERA discovered 40 novel methods for single-cell data analysis that outperformed the top human-developed methods on a public leaderboard. In epidemiology, ERA generated 14 models that outperformed the CDC ensemble and all other individual models for forecasting COVID-19 hospitalizations. ERA also produced expert-level software for geospatial analysis, neural activity prediction in zebrafish, and numerical solution of integrals, and a novel rule-based construction for time series forecasting. By devising and implementing novel solutions to diverse tasks, ERA represents a significant step towards accelerating scientific progress.