An LLM-guided tree search system autonomously creates diverse forecasting models that match or beat CDC human-curated ensembles in a 2025-2026 prospective multi-pathogen evaluation.
An AI system to help scientists write expert-level empirical software
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments\cite{hannay2009how}. 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)\cite{silver2016mastering} 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.
representative citing papers
An agentic AI workflow evolves an adaptive XGBoost quantile regression ensemble that reduces watershed-averaged forecast error by up to 29% versus California's operational forecasts for April-July runoff at 1-6 month leads across 23 Sierra Nevada sites.
LLM-guided tree search with coding agents optimizes 3D photovoltaic designs for higher diurnal energy yield after correcting for simulation exploits.
Glia deploys a multi-agent LLM workflow with reasoning, experimentation, and analysis agents to generate interpretable algorithms for request routing, scheduling, and auto-scaling in distributed GPU clusters, reaching human-expert performance levels.
WEQA proposes a query-adaptive agent framework combining LLMs with wearable data tools, achieving 24% higher accuracy than baselines on a benchmark from four open datasets, with gains in expert-rated usefulness.
A physics-guided neural network trained on collocated GOES-East and OCO-2/3 data estimates XCO2 and reproduces observed variability against held-out OCO and TCCON measurements.
TusoAI is an LLM-based agent that builds and iteratively optimizes domain-specific computational methods for scientific data analysis, outperforming expert baselines on RNA-seq denoising and earth monitoring while reporting new genetic associations.
A multi-agent LLM framework, ATHENA, autonomously designs and refines numerical PDE solvers and physics-informed models, reportedly beating expert-authored baselines.
The paper proposes the Cybersecurity AI Scientist as a modular multi-agent architecture for automating cybersecurity research, distinguished by its focus on non-stationary threats and anchored in a four-zeros risk-trust-incident-energy frame.
citing papers explorer
-
Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
An LLM-guided tree search system autonomously creates diverse forecasting models that match or beat CDC human-curated ensembles in a 2025-2026 prospective multi-pathogen evaluation.
-
Probabilistic Seasonal Streamflow Forecasting Across California's Sierra Nevada Watersheds with Agentic AI
An agentic AI workflow evolves an adaptive XGBoost quantile regression ensemble that reduces watershed-averaged forecast error by up to 29% versus California's operational forecasts for April-July runoff at 1-6 month leads across 23 Sierra Nevada sites.
-
Optimized Three-Dimensional Photovoltaic Structures with LLM guided Tree Search
LLM-guided tree search with coding agents optimizes 3D photovoltaic designs for higher diurnal energy yield after correcting for simulation exploits.
-
Glia: A Human-Inspired AI for Automated Systems Design and Optimization
Glia deploys a multi-agent LLM workflow with reasoning, experimentation, and analysis agents to generate interpretable algorithms for request routing, scheduling, and auto-scaling in distributed GPU clusters, reaching human-expert performance levels.
-
WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning
WEQA proposes a query-adaptive agent framework combining LLMs with wearable data tools, achieving 24% higher accuracy than baselines on a benchmark from four open datasets, with gains in expert-rated usefulness.
-
Quantification of atmospheric carbon dioxide from the Geostationary Operational Environmental Satellite (GOES East)
A physics-guided neural network trained on collocated GOES-East and OCO-2/3 data estimates XCO2 and reproduces observed variability against held-out OCO and TCCON measurements.
-
TusoAI: Agentic Optimization for Scientific Methods
TusoAI is an LLM-based agent that builds and iteratively optimizes domain-specific computational methods for scientific data analysis, outperforming expert baselines on RNA-seq denoising and earth monitoring while reporting new genetic associations.
-
ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms
A multi-agent LLM framework, ATHENA, autonomously designs and refines numerical PDE solvers and physics-informed models, reportedly beating expert-authored baselines.
-
Hephaestus: Toward a Cybersecurity AI Scientist
The paper proposes the Cybersecurity AI Scientist as a modular multi-agent architecture for automating cybersecurity research, distinguished by its focus on non-stationary threats and anchored in a four-zeros risk-trust-incident-energy frame.