The SDE benchmark shows LLMs lag on scientific discovery tasks relative to general science tests, with diminishing scaling returns and shared weaknesses across models.
hub
Self-Driving Laboratories for Chemistry and Materials Science.Chemical Reviews
14 Pith papers cite this work, alongside 478 external citations. Polarity classification is still indexing.
14
Pith papers citing it
478
external citations · OpenAlex
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
NIMO Controller is an MCP-based SDL orchestrator that generates a visual programming interface for human users and provides a unified backend for AI agents, validated through a color-matching case study.
Introduces CLUSTER algorithm extending quadratic-interpolation trust-region methods to handle parameter-change costs, claiming ~50% performance gains on test problems and lab experiments plus an adapted convergence guarantee.
A federated SKG built from AI-elicited expert knowledge enables seven new query types across bioanalytical subgraphs, including detection of automation-masked silent failures via the MASKED_BY relationship.
AutoLLMResearch trains agents in a multi-fidelity LLMConfig-Gym environment formulated as a long-horizon MDP to enable cross-fidelity extrapolation for automating high-cost LLM experiment configurations.
Pyomo.DoE gains callback-based support for eigenvalue optimality criteria (E- and ME-optimality) plus a new experiment-creation abstraction for uncertainty quantification in high-fidelity models.
Autonomous controllers cannot remove decision risk from target components absent from their pre-action physical records; closing that gap requires expanded access, cost, or restricted deployment.
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
A closed-loop workflow using Gaussian process surrogate modeling and Bayesian optimization, updated over ten iterations with 106 wet-lab tests, adapted from literature data to identify a cryoprotectant formulation achieving 95.15% post-thaw viability for cryomicroneedles.
The paper introduces Experiment-as-Code Labs as a declarative stack synthesizing AI agents, systems orchestration, and physical lab control for AI-driven discovery.
An affordable Arduino-based IoT setup generates real-time optical data for students to compare traversal, Bayesian, and deep learning methods in a self-driving experimental workflow.
AIMBio-Mat is a conceptual blueprint for an AI-native, FAIR, governance-aware decision layer that formulates biomedical-materials discovery as constrained multi-objective optimization under uncertainty.
An AI interoperability framework between FINALES and Kadi4Mat uses batched Bayesian optimization to explore trade-offs between shorter formation time and higher end-of-life performance in sodium-ion coin cells.
A critical review of AI surrogate models for multiscale combustion that compares supervised, unsupervised, and physics-guided methods, identifies transferability and consistency challenges, and outlines future opportunities.
citing papers explorer
-
Evaluating Large Language Models in Scientific Discovery
The SDE benchmark shows LLMs lag on scientific discovery tasks relative to general science tests, with diminishing scaling returns and shared weaknesses across models.
-
NIMO Controller: a self-driving laboratory orchestrator based on the Model Context Protocol
NIMO Controller is an MCP-based SDL orchestrator that generates a visual programming interface for human users and provides a unified backend for AI agents, validated through a color-matching case study.
-
CLUSTER: Derivative-free optimization of smooth functions with parameter-change costs
Introduces CLUSTER algorithm extending quadratic-interpolation trust-region methods to handle parameter-change costs, claiming ~50% performance gains on test problems and lab experiments plus an adapted convergence guarantee.
-
Federated Semantic Knowledge Graphs for Laboratory Workflows: A Structured Expert Elicitation Methodology Demonstrated Through Bioanalytical Workflow Twins
A federated SKG built from AI-elicited expert knowledge enables seven new query types across bioanalytical subgraphs, including detection of automation-masked silent failures via the MASKED_BY relationship.
-
AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
AutoLLMResearch trains agents in a multi-fidelity LLMConfig-Gym environment formulated as a long-horizon MDP to enable cross-fidelity extrapolation for automating high-cost LLM experiment configurations.
-
Optimal Experimental Design using Eigenvalue-Based Criteria with Pyomo.DoE
Pyomo.DoE gains callback-based support for eigenvalue optimality criteria (E- and ME-optimality) plus a new experiment-creation abstraction for uncertainty quantification in high-fidelity models.
-
Measurement-Access Risk Frontiers for Autonomous Scientific Control
Autonomous controllers cannot remove decision risk from target components absent from their pre-action physical records; closing that gap requires expanded access, cost, or restricted deployment.
-
MagicSim: A Unified Infrastructure for Executable Embodied Interaction
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
-
Agentic Discovery of Cryomicroneedle Formulations
A closed-loop workflow using Gaussian process surrogate modeling and Bayesian optimization, updated over ten iterations with 106 wet-lab tests, adapted from literature data to identify a cryoprotectant formulation achieving 95.15% post-thaw viability for cryomicroneedles.
-
Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery
The paper introduces Experiment-as-Code Labs as a declarative stack synthesizing AI agents, systems orchestration, and physical lab control for AI-driven discovery.
-
Building an Affordable Self-Driving Lab: Practical Machine Learning Experiments for Physics Education Using Internet-of-Things
An affordable Arduino-based IoT setup generates real-time optical data for students to compare traversal, Bayesian, and deep learning methods in a self-driving experimental workflow.
-
AIMBio-Mat: An AI-Native FAIR Platform for Closed-Loop Materials Discovery and Biomedical Translation
AIMBio-Mat is a conceptual blueprint for an AI-native, FAIR, governance-aware decision layer that formulates biomedical-materials discovery as constrained multi-objective optimization under uncertainty.
-
Accelerating battery research with an AI interface between FINALES and Kadi4Mat
An AI interoperability framework between FINALES and Kadi4Mat uses batched Bayesian optimization to explore trade-offs between shorter formation time and higher end-of-life performance in sodium-ion coin cells.
-
AI-Powered Surrogate Modelling for Multiscale Combustion: A Critical Review and Opportunities
A critical review of AI surrogate models for multiscale combustion that compares supervised, unsupervised, and physics-guided methods, identifies transferability and consistency challenges, and outlines future opportunities.