LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916249091440640 |
|---|---|
| author | Ma, Pingchuan Wang, Tsun-Hsuan Guo, Minghao Sun, Zhiqing Tenenbaum, Joshua B. Rus, Daniela Gan, Chuang Matusik, Wojciech |
| author_facet | Ma, Pingchuan Wang, Tsun-Hsuan Guo, Minghao Sun, Zhiqing Tenenbaum, Joshua B. Rus, Daniela Gan, Chuang Matusik, Wojciech |
| contents | Large Language Models have recently gained significant attention in scientific discovery for their extensive knowledge and advanced reasoning capabilities. However, they encounter challenges in effectively simulating observational feedback and grounding it with language to propel advancements in physical scientific discovery. Conversely, human scientists undertake scientific discovery by formulating hypotheses, conducting experiments, and revising theories through observational analysis. Inspired by this, we propose to enhance the knowledge-driven, abstract reasoning abilities of LLMs with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework: LLMs act as knowledgeable and versatile thinkers, proposing scientific hypotheses and reason about discrete components, such as physics equations or molecule structures; meanwhile, simulations function as experimental platforms, providing observational feedback and optimizing via differentiability for continuous parts, such as physical parameters. We conduct extensive experiments to demonstrate our framework's efficacy in constitutive law discovery and molecular design, unveiling novel solutions that differ from conventional human expectations yet remain coherent upon analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09783 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery Ma, Pingchuan Wang, Tsun-Hsuan Guo, Minghao Sun, Zhiqing Tenenbaum, Joshua B. Rus, Daniela Gan, Chuang Matusik, Wojciech Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Large Language Models have recently gained significant attention in scientific discovery for their extensive knowledge and advanced reasoning capabilities. However, they encounter challenges in effectively simulating observational feedback and grounding it with language to propel advancements in physical scientific discovery. Conversely, human scientists undertake scientific discovery by formulating hypotheses, conducting experiments, and revising theories through observational analysis. Inspired by this, we propose to enhance the knowledge-driven, abstract reasoning abilities of LLMs with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework: LLMs act as knowledgeable and versatile thinkers, proposing scientific hypotheses and reason about discrete components, such as physics equations or molecule structures; meanwhile, simulations function as experimental platforms, providing observational feedback and optimizing via differentiability for continuous parts, such as physical parameters. We conduct extensive experiments to demonstrate our framework's efficacy in constitutive law discovery and molecular design, unveiling novel solutions that differ from conventional human expectations yet remain coherent upon analysis. |
| title | LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2405.09783 |