Chuang Gan, Joshua Tenenbaum, Zhiqing Sun, Pingchuan Ma, Wojciech Matusik, Daniela Rus, Minghao Guo, Tsun-Hsuan Wang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.09783")
get_code_for_paper("2405.09783")
have("2405.09783")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2405.09783.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2405.09783)
Connect an agent — have() is free.