Science Agents

Science Agents

• 2024-06-19: LLMatDesign: Autonomous Materials Discovery with Large Language Models
• 2024-08-12: Sakana AI: AI Scientist; The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery (code)
• 2024-09-09: SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning (code)
• 2024-09-11: PaperQA2: Language Models Achieve Superhuman Synthesis of Scientific Knowledge (𝕏 post, code)
• 2024-10-17: Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems
• 2024-10-28: Large Language Model-Guided Prediction Toward Quantum Materials Synthesis
• 2024-12-06: The Virtual Lab: AI Agents Design New SARS-CoV-2 Nanobodies with Experimental Validation (writeup: Virtual lab powered by ‘AI scientists’ super-charges biomedical research: Could human–AI collaborations be the future of interdisciplinary studies?)

Autonomous Ideation

• 2024-09: Mining Causality: AI-Assisted Search for Instrumental Variables

Data Visualization

• 2024-10: Data Formulator: Create Rich Visualization with AI iteratively (video, code)
• Julius AI: Analyze your data with computational AI

Adapting LLMs to Science

• 2023-06: Domain-specific chatbots for science using embeddings
• 2024-10: Personalization of Large Language Models: A Survey
• 2024-11: Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation

AI/ML Methods tailored to Science

Symbolic Regression

• 2024-09: Symbolic Regression with a Learned Concept Library

Literature Discovery

• FutureHouse
  • hasanyone
  • PaperQA2
• Lumina
• Automated-AI-Web-Researcher-Ollama

Commercial

• Cusp AI: Materials/AI

AI/ML Methods co-opted for Science

Mechanistic Interpretability

Train large model on science data. Then apply mechanistic interpretability (e.g. sparse autoencoders, SAE) to the feature/activation space.

• Mechanistic interpretability for protein language models (visualizer, code, SAE)
• Markov Bio: Through a Glass Darkly: Mechanistic Interpretability as the Bridge to End-to-End Biology (quick description, background info on recent bio progress)

Uncertainty

• 2024-10: entropix: Entropy Based Sampling and Parallel CoT Decoding
• 2024-10: Taming Overconfidence in LLMs: Reward Calibration in RLHF

AI Science Systems

Inorganic Materials Discovery

• 2023-11: Scaling deep learning for materials discovery
• 2023-11: An autonomous laboratory for the accelerated synthesis of novel materials
• 2024-10: Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models (code, datasets, checkpoints, blogpost)

Chemistry

• 2023-12: Autonomous chemical research with large language models (Coscientist)

Impact of AI in Science

• 2024-11: Artificial Intelligence, Scientific Discovery, and Product Innovation

See Also

• AI agents
• Nanobot.chat: Intelligent AI for the labnetwork @ mtl.mit.edu forum