Article

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

2025-10-24

Abstract excerpt

<title>Abstract</title> <p>The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments. To address this, we present 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) to systematically improve the quality metric and int...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 3eee0056-811d-5a74-88a9-906923b0ce24
DOI: 10.21203/rs.3.rs-7610233/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

An AI system to help scientists write expert-level empirical softwareDOI 10.21203/rs.3.rs-7610233/v1Read

Out-of-the-box bioinformatics capabilities of large language models (LLMs)Semantic proximity Read

Orion: Towards Lab Automation with Computer-Using AgentsSemantic proximity Read

Artificial Intelligence in Biomedicine: Systematic ReviewSemantic proximity Read

A Process-Centric Survey of AI for Scientific Discovery Through the EXHYTE FrameworkSemantic proximity Read

Will generative AI help solve systematic literature reviews? Evidence from a 2-year research programmeSemantic proximity Read

Prompting large language models for quality ecological statisticsSemantic proximity Read

CARDBiomedBench: A Benchmark for Evaluating Large Language Model Performance in Biomedical ResearchSemantic proximity Read

Inductive reasoning with large language models: a simulated randomized controlled trial for epilepsySemantic proximity Read

LLM-assisted screening and extraction for systematic reviews: workload reduction and refusal-driven missingness in a land-use evidence synthesisSemantic proximity Read

Agentic AI for Streamlining Title and Abstract Screening: Addressing Precision and evaluating calibration of AI guardrailsSemantic proximity Read

Artificial intelligence resources for the screening of titles and abstracts in systematic reviews: a scoping reviewSemantic proximity Read

When AI Meets the FDA: An Evaluation of Large Language Models Performance in Regulatory and Clinical Trial Data Extraction, Synthesis, and AnalysisSemantic proximity Read