The pipeline tests if LLMs can design scientific experiments.
Pavel Izmailov#376
Can LLMs discover new laws of physics?
We present DiscoverPhysics, a pipeline to benchmark LLM agents on experimentation, analysis & discovery. Co-led by @LindsayMSmith3 w/ Peter Melchior,@kdqg1 @andrewgwils @Pavel_Izmailov,Carolina Cuesta-Lázaro https://arxiv.org/abs/2605.26087 1/10
Can LLMs discover new laws of physics?
We present DiscoverPhysics, a pipeline to benchmark LLM agents on experimentation, analysis and discovery. https://arxiv.org/abs/2605.26087 Co-led by @LindsayMSmith3 w/ Peter Melchior, @kdqg1 @andrewgwils @Pavel_Izmailov Carol Cuesta-Lazaro 1/10
So excited about this project. Despite all the talk about AGI, AI has barely scratched the surface of discovering scientific theories or even giving us new scientific insights. DiscoverPhysics is a benchmark for the future.
Can LLMs discover new laws of physics?
We present DiscoverPhysics, a pipeline to benchmark LLM agents on experimentation, analysis and discovery. https://arxiv.org/abs/2605.26087 Co-led by @LindsayMSmith3 w/ Peter Melchior, @kdqg1 @andrewgwils @Pavel_Izmailov Carol Cuesta-Lazaro 1/10
The pipeline tests if LLMs can design scientific experiments.
Pavel Izmailov#376Can LLMs discover new laws of physics?
We present DiscoverPhysics, a pipeline to benchmark LLM agents on experimentation, analysis & discovery. Co-led by @LindsayMSmith3 w/ Peter Melchior,@kdqg1 @andrewgwils @Pavel_Izmailov,Carolina Cuesta-Lázaro https://arxiv.org/abs/2605.26087 1/10
