| Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System | Oct 12, 2024 | Experimental Designscientific discovery | CodeCode Available | 2 |
| Accelerating Material Design with the Generative Toolkit for Scientific Discovery | Jul 8, 2022 | Drug DiscoveryMaterials Screening | CodeCode Available | 2 |
| From Generalist to Specialist: A Survey of Large Language Models for Chemistry | Dec 28, 2024 | scientific discoverySurvey | CodeCode Available | 2 |
| HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation | Apr 15, 2025 | Benchmarkingscientific discovery | CodeCode Available | 2 |
| SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding | Aug 28, 2024 | Instruction Followingscientific discovery | CodeCode Available | 2 |
| Ten Quick Tips for Harnessing the Power of ChatGPT/GPT-4 in Computational Biology | Mar 29, 2023 | ChatbotPrompt Engineering | CodeCode Available | 2 |
| BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology | Feb 28, 2025 | Multiple-choicescientific discovery | CodeCode Available | 2 |
| Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data | May 16, 2024 | Active Learningscientific discovery | CodeCode Available | 2 |
| AI-Newton: A Concept-Driven Physical Law Discovery System without Prior Physical Knowledge | Apr 2, 2025 | scientific discovery | CodeCode Available | 2 |
| Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples | Jun 9, 2024 | ARCDiversity | CodeCode Available | 2 |
| Protein Large Language Models: A Comprehensive Survey | Feb 21, 2025 | ArticlesProtein Structure Prediction | CodeCode Available | 2 |
| ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery | Oct 7, 2024 | scientific discovery | CodeCode Available | 2 |
| AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research | May 17, 2025 | scientific discovery | CodeCode Available | 2 |
| OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI | Jun 18, 2024 | Benchmarkingscientific discovery | CodeCode Available | 2 |
| Multi-Fidelity Active Learning with GFlowNets | Jun 20, 2023 | Active LearningBayesian Optimization | CodeCode Available | 2 |
| BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments | May 27, 2024 | AI AgentBayesian Optimization | CodeCode Available | 2 |
| LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery | May 16, 2024 | Bilevel Optimizationscientific discovery | CodeCode Available | 2 |
| DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra | Feb 13, 2025 | DecoderDe novo molecule generation from MS/MS spectrum (bonus chemical formulae) | CodeCode Available | 2 |
| Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery | Jul 9, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms | May 27, 2025 | Bayesian OptimizationBenchmarking | CodeCode Available | 2 |
| MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses | Oct 9, 2024 | scientific discoveryvalid | CodeCode Available | 2 |
| SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models | Jan 15, 2024 | MathMathematical Reasoning | CodeCode Available | 2 |
| InductionBench: LLMs Fail in the Simplest Complexity Class | Feb 20, 2025 | scientific discovery | CodeCode Available | 1 |
| GraphGPT: Graph Learning with Generative Pre-trained Transformers | Dec 31, 2023 | DecoderGraph Learning | CodeCode Available | 1 |
| Going From Molecules to Genomic Variations to Scientific Discovery: Intelligent Algorithms and Architectures for Intelligent Genome Analysis | May 16, 2022 | scientific discovery | CodeCode Available | 1 |
