The SDE benchmark shows LLMs lag on scientific discovery tasks relative to general science tests, with diminishing scaling returns and shared weaknesses across models.
Carter, Xin Zhou, Matthew Wheeler, Jonathan A
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
Affinage uses a two-pass LLM system to generate literature-derived mechanistic annotations for nearly the entire human proteome, outperforming UniProt on 99.1% of genes per an LLM judge.
Starling, a multi-agent LLM system, extracts ~6.3 million nuanced structured records from PubMed across six tasks with reported error rates of 0.6-7.7%, lower than several curated databases.
StructBioReasoner is a scalable multi-agent system that designs IDP-targeting biologics, with over 50% of 787 candidates for Der f 21 showing better binding free energy than human-designed references.
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
CodeDistiller distills 250 materials-science GitHub repositories into vetted code libraries that improve the accuracy and scientific soundness of experiments generated by ASD agents.
Proposes a three-tier data readiness framework (FAIR to AI-ready to space-ready) plus an international governance body to enable AI use of space biology data.
BioInsight is a multi-agent system that generates interactive, provenance-preserving biomedical evidence interfaces from disease names and protein data.
Agentic-J is a multi-agent AI assistant that converts natural language descriptions of biological image analysis tasks into executable, reproducible scripts for ImageJ/Fiji with specialised sub-agents for plugin management, code generation, debugging and reporting.
Vibe Medicine proposes directing AI agents via natural language for end-to-end biomedical workflows using LLMs, agent frameworks, and a curated collection of over 1,000 medical skills.
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.
-
Affinage: genome-scale mechanistic gene annotation from the published literature
Affinage uses a two-pass LLM system to generate literature-derived mechanistic annotations for nearly the entire human proteome, outperforming UniProt on 99.1% of genes per an LLM judge.
-
Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale
Starling, a multi-agent LLM system, extracts ~6.3 million nuanced structured records from PubMed across six tasks with reported error rates of 0.6-7.7%, lower than several curated databases.
-
Scalable Agentic Reasoning for Designing Biologics Targeting Intrinsically Disordered Proteins
StructBioReasoner is a scalable multi-agent system that designs IDP-targeting biologics, with over 50% of 787 candidates for Der f 21 showing better binding free energy than human-designed references.
-
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
SAGE with MHFA improves failure recovery in autonomous research agents, raising metrics-bearing outputs from 42% to 92% on a 12-topic benchmark versus single-reflection baselines.
-
CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents
CodeDistiller distills 250 materials-science GitHub repositories into vetted code libraries that improve the accuracy and scientific soundness of experiments generated by ASD agents.
-
Building AI-Ready Data Systems for Space Life Sciences, Aerospace Medicine, and Deep Space Exploration
Proposes a three-tier data readiness framework (FAIR to AI-ready to space-ready) plus an international governance body to enable AI use of space biology data.
-
BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
BioInsight is a multi-agent system that generates interactive, provenance-preserving biomedical evidence interfaces from disease names and protein data.
-
Agentic-J: An AI Agent for Biological Microscopy Image Analysis
Agentic-J is a multi-agent AI assistant that converts natural language descriptions of biological image analysis tasks into executable, reproducible scripts for ImageJ/Fiji with specialised sub-agents for plugin management, code generation, debugging and reporting.
-
Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work
Vibe Medicine proposes directing AI agents via natural language for end-to-end biomedical workflows using LLMs, agent frameworks, and a curated collection of over 1,000 medical skills.