AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology I: Literature Review

arXiv:2607.25672 · astro-ph.IM, astro-ph.CO, cs.CL, gr-qc · Submitted 2026-07-28 · Read on arXiv

Anamaria Hell, Kateryna Vovk, Veena Krishnaraj, Jia Liu, Kosuke Aizawa, Adrian E. Bayer, Linda Blot, Jessica Cowell, Suyog Garg, Jonathan Grée, Ben Horowitz, Masaya Ichikawa, Kanyuni Iemoto, Keigo Kondo, Zacharie Lorsin, Kevin McCarthy, Jamie Robinson, Miguel Ruiz-Granda, Leander Thiele, Ievgen Vovk, Mingshen Zhou

astro-ph.IM, astro-ph.CO, cs.CL, gr-qc

Submitted: 2026-07-28

Comments: 12 pages, 3 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AGN — 20× in this paper · explained in 1 episode
• ChatGPT Deep Research — 15× in this paper
• Hallucination — 13× in this paper · explained in 3 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Pulsar Timing Array — 5× in this paper
• Verification — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• N-body simulations — 2× in this paper · explained in 2 episodes
• Weak Lensing — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Active Galactic Nuclei (AGN) — 1× in this paper · explained in 1 episode
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• pulsar timing arrays — 1× in this paper · explained in 2 episodes

Sources

• Can large language models provide useful feedback on research papers? A large-scale empirical analysis
• FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks
• AstroLLaMA: Towards Specialized Foundation Models in Astronomy
• Mitigating the Bias of Large Language Model Evaluation
• DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• LLM Evaluators Recognize and Favor Their Own Generations
• Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
• Self-Preference Bias in LLM-as-a-Judge
• Can AI-Generated Text be Reliably Detected?
• Assisting Research Proposal Writing with Large Language Models: Evaluation and Refinement
• Can Large Language Models Evaluate Grant Proposal Quality? Revisiting the Wenner{\aa}s and Wold Peer Review Data
• Evaluating LLM-Based Grant Proposal Review via Structured Perturbations
• The Denario project: Deep knowledge AI agents for scientific discovery
• PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
• LLMs with in-context learning for Algorithmic Theoretical Physics
• The HalfDome Multi-Survey Cosmological Simulations: N-body Simulations
• The strong couplings of massive Yang-Mills theory

Related papers

• A signal dedispersion algorithm for imaging-based transient searches
• AVICA: A fully automated CASA pipeline for large volume VLBI data calibration
• Spectral Map Making with SPHEREx
• Long-Integration Magnetar Burst Observatory (LIMBO): Instrument Summary and Early FRB Rate Constraints
• Towards independent event horizon imaging of the supermassive black holes in M87 and the Milky Way
• A PINK update: Improvements to the CELEBI fast radio burst data reduction and analysis pipeline