# TusoAI: Agentic Optimization for Scientific Methods

arXiv: https://arxiv.org/abs/2509.23986 · HTML: https://mlsanity.com/paper/2509.23986/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 98 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 20 of 20)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)
- [OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs](https://mlsanity.com/paper/2411.14199/) (2024)
- [Large language models surpass human experts in predicting neuroscience results](https://mlsanity.com/paper/2403.03230/) (2024)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement](https://mlsanity.com/paper/2506.15692/) (2025)
- [HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units](https://mlsanity.com/paper/2008.04063/) (2020)
- [NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks](https://mlsanity.com/paper/2110.05668/) (2021)
- [CellForge: Agentic Design of Virtual Cell Models](https://mlsanity.com/paper/2508.02276/) (2025)
- [sEMG Gesture Recognition with a Simple Model of Attention](https://mlsanity.com/paper/2006.03645/) (2020)
- [Large Language Models for Code Generation: The Practitioners Perspective](https://mlsanity.com/paper/2501.16998/) (2025)
- [Bayesian Modeling of Spatial Molecular Profiling Data via Gaussian Process](https://mlsanity.com/paper/2012.03326/) (2020)

## Built on by (most cited first, 4 of 4)

- [SpatialEpiBench: Benchmarking Spatial Information and Epidemic Priors in Forecasting](https://mlsanity.com/paper/2605.06530/) (2026)
- [CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction](https://mlsanity.com/paper/2605.07335/) (2026)
- [A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline](https://mlsanity.com/paper/2606.07718/) (2026)
- [SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm](https://mlsanity.com/paper/2610.20431/) (2026)

## Abstract (arXiv)

Scientific discovery is often slowed by the manual development of computational tools needed to analyze complex experimental data. Building such tools is costly and time-consuming because scientists must iteratively review literature, test modeling and scientific assumptions against empirical data, and implement these insights into efficient software. Large language models (LLMs) have demonstrated strong capabilities in synthesizing literature, reasoning with empirical data, and generating domain-specific code, offering new opportunities to accelerate computational method development. Existing LLM-based systems either focus on performing scientific analyses using existing computational methods or on developing computational methods or models for general machine learning without effectively integrating the often unstructured knowledge specific to scientific domains. Here, we introduce TusoAI , an agentic AI system that takes a scientific task description with an evaluation function and autonomously develops and optimizes computational methods for the application. TusoAI integrates domain knowledge into a knowledge tree representation and performs iterative, domain-specific optimization and model diagnosis, improving performance over a pool of candidate solutions. We conducted comprehensive benchmark evaluations demonstrating that TusoAI outperforms state-of-the-art expert methods, MLE agents, and scientific AI agents across diverse tasks, such as single-cell RNA-seq data denoising and satellite-based earth monitoring. Applying TusoAI to two key open problems in genetics improved existing computational methods and uncovered novel biology, including 9 new associations between autoimmune diseases and T cell subtypes and 7 previously unreported links between disease variants linked to their target genes. Our code is publicly available at https://github.com/Alistair-Turcan/TusoAI.