DeepInflation: an AI agent for research and model discovery of inflation

TL;DR

DeepInflation is an AI agent that combines LLMs, symbolic regression, and knowledge bases to autonomously discover and verify inflationary cosmology models aligned with current observations.

Contribution

It introduces a multi-agent framework that automates the exploration and validation of inflationary potentials using natural language and theoretical grounding.

Findings

Successfully discovers viable inflationary potentials consistent with observations

Provides accurate theoretical context for obscure inflation scenarios

Demonstrates autonomous exploration of the inflationary landscape

Abstract

We present \textbf{DeepInflation}, an AI agent designed for research and model discovery in inflationary cosmology. Built upon a multi-agent architecture, \textbf{DeepInflation} integrates Large Language Models (LLMs) with a symbolic regression (SR) engine and a retrieval-augmented generation (RAG) knowledge base. This framework enables the agent to automatically explore and verify the vast landscape of inflationary potentials while grounding its outputs in established theoretical literature. We demonstrate that \textbf{DeepInflation} can successfully discover simple and viable single-field slow-roll inflationary potentials consistent with the latest observations (here ACT DR6 results as example) or any given $n_s$ and $r$, and provide accurate theoretical context for obscure inflationary scenarios. \textbf{DeepInflation} serves as a prototype for a new generation of autonomous scientific discovery engines in cosmology, which enables researchers and non-experts alike to explore the inflationary landscape using natural language. This agent is available at https://github.com/pengzy-cosmo/DeepInflation.