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

2026/01/14 by Ze-Yu Peng, Hao-Shi Yuan, Qi Lai +4 · 1 voice
Physics and Astronomy · Computer Science · #astro-ph.CO #cs.AI #cs.CE #gr-qc #hep-th

paper · pdf

arxiv published 2026/01/14 · arxiv updated 2026/06/17

Abstract

We present DeepInflation, an AI agent designed for research and model discovery in inflationary cosmology. Built upon a multi-agent architecture, 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 DeepInflation can successfully discover simple and viable single-field slow-roll inflationary potentials consistent with the latest observations (with the ACT DR6 results taken as an example) or any given n_s and r, and provide accurate theoretical context for obscure inflationary scenarios. 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.

Citations

• Introduction to Symbolic Regression in the Physical Sciences
• A Survey of AI Scientists
• Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
• LLM-Meta-SR: In-Context Learning for Evolving Selection Operators in Symbolic Regression
• Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks
• LLM4SR: A Survey on Large Language Models for Scientific Research
• Symbolic Regression with a Learned Concept Library
• Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions
• Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
• A Survey of Large Language Models
• Distributing Accountability, Not Capability: Phase Separation and the LLM Workflow Quadrant in Autonomous AI Agent Architectures
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Discussions

• #arXiv DeepInflation: an AI agent for research and model discovery of inflation arxiv.org/abs/2601.14288 it integrates LLMs with a symbolic regression engine and a retrieval-augmented generation knowl [bsky, 4 points, 0 comments]

Related

• Inflation and Precision Cosmology
• Using Artificial Intelligence to aid Scientific Discovery of Climate Tipping Points
• An Exposition on Inflationary Cosmology
• Testing Inflationary Cosmology
• Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research