Difference between revisions of "Science Agents"
KevinYager (talk | contribs) (→Science Agents) |
KevinYager (talk | contribs) (→Autonomous Ideation) |
||
| (4 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | == | + | |
| − | + | =AI Use-cases for Science= | |
| − | + | ||
| − | + | ==Literature== | |
| − | * | + | ===AI finding links in literature=== |
| − | + | * 2019-07: [https://doi.org/10.1038/s41586-019-1335-8 Unsupervised word embeddings capture latent knowledge from materials science literature] | |
| − | + | * 2024-11: [https://doi.org/10.1038/s41562-024-02046-9 Large language models surpass human experts in predicting neuroscience results] | |
| − | * 2024- | ||
| − | |||
| − | |||
==Autonomous Ideation== | ==Autonomous Ideation== | ||
* 2024-09: [https://arxiv.org/abs/2409.14202 Mining Causality: AI-Assisted Search for Instrumental Variables] | * 2024-09: [https://arxiv.org/abs/2409.14202 Mining Causality: AI-Assisted Search for Instrumental Variables] | ||
| − | + | * 2024-12: [https://arxiv.org/abs/2412.07977 Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events] | |
| − | |||
| − | * 2024- | ||
| − | |||
==Adapting LLMs to Science== | ==Adapting LLMs to Science== | ||
| Line 46: | Line 40: | ||
* 2024-10: [https://arxiv.org/abs/2410.09724 Taming Overconfidence in LLMs: Reward Calibration in RLHF] | * 2024-10: [https://arxiv.org/abs/2410.09724 Taming Overconfidence in LLMs: Reward Calibration in RLHF] | ||
| − | ==AI Science Systems | + | =Science Agents= |
| + | * 2024-01-13: [https://arxiv.org/abs/2401.06949 ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization] ([https://www.youtube.com/watch?v=N6qMMwJ8hKQ video]) | ||
| + | * 2024-06-19: [https://arxiv.org/abs/2406.13163 LLMatDesign: Autonomous Materials Discovery with Large Language Models] | ||
| + | * 2024-08-12: [https://sakana.ai/ Sakana AI]: [https://sakana.ai/ai-scientist/ AI Scientist]; [https://arxiv.org/abs/2408.06292 The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery] ([https://github.com/SakanaAI/AI-Scientist code]) | ||
| + | * 2024-09-09: [https://arxiv.org/abs/2409.05556 SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning] ([https://github.com/lamm-mit/SciAgentsDiscovery code]) | ||
| + | * 2024-09-11: PaperQA2: [https://paper.wikicrow.ai/ Language Models Achieve Superhuman Synthesis of Scientific Knowledge] ([https://x.com/SGRodriques/status/1833908643856818443 𝕏 post], [https://github.com/Future-House/paper-qa code]) | ||
| + | * 2024-10-17: [https://arxiv.org/abs/2410.13768 Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems] | ||
| + | * 2024-10-28: [https://arxiv.org/abs/2410.20976 Large Language Model-Guided Prediction Toward Quantum Materials Synthesis] | ||
| + | * 2024-12-06: [https://www.biorxiv.org/content/10.1101/2024.11.11.623004v1 The Virtual Lab: AI Agents Design New SARS-CoV-2 Nanobodies with Experimental Validation] (writeup: [https://www.nature.com/articles/d41586-024-01684-3 Virtual lab powered by ‘AI scientists’ super-charges biomedical research: Could human–AI collaborations be the future of interdisciplinary studies?]) | ||
| + | * 2024-12-11: Google [https://blog.google/products/gemini/google-gemini-deep-research/ Deep Research] | ||
| + | |||
| + | =AI Science Systems= | ||
===Inorganic Materials Discovery=== | ===Inorganic Materials Discovery=== | ||
* 2023-11: [https://doi.org/10.1038/s41586-023-06735-9 Scaling deep learning for materials discovery] | * 2023-11: [https://doi.org/10.1038/s41586-023-06735-9 Scaling deep learning for materials discovery] | ||
| Line 55: | Line 60: | ||
* 2023-12: [https://doi.org/10.1038/s41586-023-06792-0 Autonomous chemical research with large language models] (Coscientist) | * 2023-12: [https://doi.org/10.1038/s41586-023-06792-0 Autonomous chemical research with large language models] (Coscientist) | ||
| − | + | =Impact of AI in Science= | |
* 2024-11: [https://aidantr.github.io/files/AI_innovation.pdf Artificial Intelligence, Scientific Discovery, and Product Innovation] | * 2024-11: [https://aidantr.github.io/files/AI_innovation.pdf Artificial Intelligence, Scientific Discovery, and Product Innovation] | ||
| − | ==See Also | + | =Related Tools= |
| + | ==Data Visualization== | ||
| + | * 2024-10: [https://www.microsoft.com/en-us/research/blog/data-formulator-exploring-how-ai-can-help-analysts-create-rich-data-visualizations/ Data Formulator: Create Rich Visualization with AI iteratively] ([https://www.microsoft.com/en-us/research/video/data-formulator-create-rich-visualization-with-ai-iteratively/ video], [https://github.com/microsoft/data-formulator code]) | ||
| + | * [https://julius.ai/ Julius AI]: Analyze your data with computational AI | ||
| + | |||
| + | =See Also= | ||
* [[AI agents]] | * [[AI agents]] | ||
* [https://nanobot.chat/ Nanobot.chat]: Intelligent AI for the labnetwork @ mtl.mit.edu forum | * [https://nanobot.chat/ Nanobot.chat]: Intelligent AI for the labnetwork @ mtl.mit.edu forum | ||
Latest revision as of 10:31, 14 December 2024
Contents
AI Use-cases for Science
Literature
AI finding links in literature
- 2019-07: Unsupervised word embeddings capture latent knowledge from materials science literature
- 2024-11: Large language models surpass human experts in predicting neuroscience results
Autonomous Ideation
- 2024-09: Mining Causality: AI-Assisted Search for Instrumental Variables
- 2024-12: Thinking Fast and Laterally: Multi-Agentic Approach for Reasoning about Uncertain Emerging Events
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
Literature Discovery
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
Science Agents
- 2024-01-13: ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization (video)
- 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?)
- 2024-12-11: Google Deep Research
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
Related Tools
Data Visualization
- 2024-10: Data Formulator: Create Rich Visualization with AI iteratively (video, code)
- Julius AI: Analyze your data with computational AI
See Also
- AI agents
- Nanobot.chat: Intelligent AI for the labnetwork @ mtl.mit.edu forum
