Difference between revisions of "Science Agents"

From GISAXS
Jump to: navigation, search
(→‎Autonomous Ideation)
(→‎Specific)
 
(9 intermediate revisions by the same user not shown)
Line 38: Line 38:
 
* 2025-02: [https://arxiv.org/abs/2502.13025 Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks]
 
* 2025-02: [https://arxiv.org/abs/2502.13025 Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks]
 
* 2025-06: [https://arxiv.org/abs/2506.00794 Predicting Empirical AI Research Outcomes with Language Models]
 
* 2025-06: [https://arxiv.org/abs/2506.00794 Predicting Empirical AI Research Outcomes with Language Models]
 +
* 2025-06: [https://arxiv.org/abs/2506.20803 The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas]
  
 
==Adapting LLMs to Science==
 
==Adapting LLMs to Science==
Line 88: Line 89:
  
 
===Materials===
 
===Materials===
 +
* 2024-12: [https://www.nature.com/articles/s41467-024-54639-7 Crystal structure generation with autoregressive large language modeling
 
* 2025-03: [https://arxiv.org/abs/2503.03965 All-atom Diffusion Transformers: Unified generative modelling of molecules and materials]
 
* 2025-03: [https://arxiv.org/abs/2503.03965 All-atom Diffusion Transformers: Unified generative modelling of molecules and materials]
  
Line 95: Line 97:
 
* 2025-02: [https://www.nature.com/articles/s42256-025-00994-z Large language models for scientific discovery in molecular property prediction]
 
* 2025-02: [https://www.nature.com/articles/s42256-025-00994-z Large language models for scientific discovery in molecular property prediction]
 
* [https://x.com/vant_ai/status/1903070297991110657 2025-03]: [https://www.vant.ai/ Vant AI] [https://www.vant.ai/neo-1 Neo-1]: atomistic foundation model (small molecules, proteins, etc.)
 
* [https://x.com/vant_ai/status/1903070297991110657 2025-03]: [https://www.vant.ai/ Vant AI] [https://www.vant.ai/neo-1 Neo-1]: atomistic foundation model (small molecules, proteins, etc.)
 +
* 2025-07: [https://arxiv.org/abs/2507.07456 General purpose models for the chemical sciences]
  
 
===Biology===
 
===Biology===
Line 151: Line 154:
 
* 2024-10: [https://www.cell.com/cell/fulltext/S0092-8674(24)01070-5?target=_blank Empowering biomedical discovery with AI agents]
 
* 2024-10: [https://www.cell.com/cell/fulltext/S0092-8674(24)01070-5?target=_blank Empowering biomedical discovery with AI agents]
 
* 2025-01: [https://pubs.rsc.org/en/content/articlehtml/2024/sc/d4sc03921a A review of large language models and autonomous agents in chemistry] ([https://github.com/ur-whitelab/LLMs-in-science github])
 
* 2025-01: [https://pubs.rsc.org/en/content/articlehtml/2024/sc/d4sc03921a A review of large language models and autonomous agents in chemistry] ([https://github.com/ur-whitelab/LLMs-in-science github])
 +
* 2025-07: [https://arxiv.org/abs/2507.01903 AI4Research: A Survey of Artificial Intelligence for Scientific Research]
  
 
==Specific==
 
==Specific==
Line 164: Line 168:
 
* See also: [[AI_Agents#Deep_Research|AI Agents > Deep Research]]
 
* See also: [[AI_Agents#Deep_Research|AI Agents > Deep Research]]
 
* 2025-04-08: Sakana: [https://pub.sakana.ai/ai-scientist-v2/paper/paper.pdf The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search] ([https://github.com/SakanaAI/AI-Scientist-v2 code])
 
* 2025-04-08: Sakana: [https://pub.sakana.ai/ai-scientist-v2/paper/paper.pdf The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search] ([https://github.com/SakanaAI/AI-Scientist-v2 code])
 +
* 2025-07: [https://arxiv.org/abs/2507.14267 DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation]
  
 
==Science Multi-Agent Setups==
 
==Science Multi-Agent Setups==
Line 173: Line 178:
 
* 2025-01: [https://arxiv.org/abs/2501.13299 Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents]
 
* 2025-01: [https://arxiv.org/abs/2501.13299 Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents]
 
* 2025-02: [https://storage.googleapis.com/coscientist_paper/ai_coscientist.pdf Towards an AI co-scientist] (Google blog post: [https://research.google/blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/ Accelerating scientific breakthroughs with an AI co-scientist])
 
* 2025-02: [https://storage.googleapis.com/coscientist_paper/ai_coscientist.pdf Towards an AI co-scientist] (Google blog post: [https://research.google/blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/ Accelerating scientific breakthroughs with an AI co-scientist])
 +
* 2025-06: [https://zenodo.org/records/15693353 The Discovery Engine]
 +
** 2025-07: [https://arxiv.org/abs/2507.00964 Benchmarking the Discovery Engine] ([https://www.leap-labs.com/blog/how-we-replicated-five-peer-reviewed-papers-in-five-hours blog])
  
 
===Inorganic Materials Discovery===
 
===Inorganic Materials Discovery===
Line 186: Line 193:
 
* 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)
 
* 2024-11: [https://www.nature.com/articles/s41467-024-54457-x An automatic end-to-end chemical synthesis development platform powered by large language models]
 
* 2024-11: [https://www.nature.com/articles/s41467-024-54457-x An automatic end-to-end chemical synthesis development platform powered by large language models]
 +
* 2025-06: [https://paper.ether0.ai/ Training a Scientific Reasoning Model for Chemistry]
 +
* 2025-06: [https://arxiv.org/abs/2506.06363 ChemGraph: An Agentic Framework for Computational Chemistry Workflows] ([https://github.com/argonne-lcf/ChemGraph code])
 +
 +
===Bio===
 +
* 2025-07: [https://arxiv.org/abs/2507.01485 BioMARS: A Multi-Agent Robotic System for Autonomous Biological Experiments]
  
 
==LLMs Optimized for Science==
 
==LLMs Optimized for Science==
 
* 2022-11: [https://arxiv.org/abs/2211.09085 Galactica: A Large Language Model for Science]
 
* 2022-11: [https://arxiv.org/abs/2211.09085 Galactica: A Large Language Model for Science]
 +
* 2024-12: [https://www.nature.com/articles/s41467-024-54639-7 Crystal structure generation with autoregressive large language modeling
 
* 2025-02: [https://arxiv.org/abs/2502.13107 MatterChat: A Multi-Modal LLM for Material Science]
 
* 2025-02: [https://arxiv.org/abs/2502.13107 MatterChat: A Multi-Modal LLM for Material Science]
 
* 2025-03: [https://arxiv.org/abs/2503.17604 OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery]
 
* 2025-03: [https://arxiv.org/abs/2503.17604 OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery]

Latest revision as of 11:42, 22 July 2025

AI Use-cases for Science

Literature

LLM extract data from papers

AI finding links in literature

(Pre) Generate Articles

Explanation

Autonomous Ideation

Adapting LLMs to Science

AI/LLM Control of Scientific Instruments/Facilities

AI/ML Methods tailored to Science

Regression (Data Fitting)

Tabular Classification/Regression

Symbolic Regression

Literature Discovery

Commercial

Bio

AI/ML Methods in Science

Imaging

Materials

Chemistry

Biology

Medicine

See: AI_Agents#Medicine

Successes

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.

Uncertainty

Science Benchmarks

Science Agents

Reviews

Specific

Science Multi-Agent Setups

AI Science Systems

Inorganic Materials Discovery

Chemistry

Bio

LLMs Optimized for Science

Impact of AI in Science

Related Tools

Literature Search

Data Visualization

Generative

Chemistry

Science Datasets

See Also

Retrieved from "http://gisaxs.com/index.php?title=Science_Agents&oldid=8089"