AI assistant tackles cosmology's trickiest math express
The Universe's expansion is accelerating, and maybe gravity doesn't work the way we think. Physicists come up with alternative theories, but to test them, they need to calculate how ripples after the Big Bang grew into galaxies. Such calculations involve long equations with hundreds of terms, where it's easy to get lost. Georges Lemaître and Edwin Hubble laid the groundwork, but now a machine takes over the grunt work.
The neural network Claude, hooked up to the math package Maple, works like a robot chef: you give it a recipe (the initial theory), it measures out ingredients (simplifies formulas), mixes them (substitutes expressions), and bakes up predictions. The physicist just has to taste-test the result — compare it with observations. On the problem of cosmic perturbations, after a couple of examples, the AI handled most new cases, but sometimes slipped up — flipping signs or dropping terms.
Such an assistant could speed up the hunt for the secrets of dark energy many times over, or even show how the expansion can happen without it. For now, human oversight is still essential, but it's clear: the future of cosmology demands a symbiosis of living and machine intelligence.
Original abstract
as written by the authors arXiv:2605.08212
There is an increasing number of algorithmic computations in theoretical physics. These, while conceptually simple, can nevertheless be time-consuming and contain subtleties that should not be overlooked. Given the recent improvement of Large Language Models (LLM), it is natural to investigate whether LLMs equipped with a computer algebra system (CAS) runtime and sufficiently informative context can reliably carry out these algorithmic tasks. In this work, we interface Claude with Maple, and apply this framework to cosmological perturbations in modified theories of gravity. We demonstrate the current capabilities of this approach, the typical failures, and how the same can be improved. We find that a frontier LLM supplied with worked examples is able to solve most test problems.
The first calculations of cosmic ripples were done with pencil and paper. One arithmetic slip, and a discovery could be delayed by a decade.