Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909034246832128 |
|---|---|
| author | Islam, Tousif Wadekar, Digvijay Venumadhav, Tejaswi Zaldarriaga, Matias Mehta, Ajit Kumar Roulet, Javier Zackay, Barak |
| author_facet | Islam, Tousif Wadekar, Digvijay Venumadhav, Tejaswi Zaldarriaga, Matias Mehta, Ajit Kumar Roulet, Javier Zackay, Barak |
| contents | Fast surrogate models for expensive simulations are now essential across the sciences, yet they typically operate as black boxes. We present \texttt{GWAgent}, a large language model (LLM)-based workflow that constructs interpretable analytic surrogates directly from simulation data. Surrogate modeling is well suited to agentic workflows because candidate models can be quantitatively validated against ground-truth simulations at each iteration. As a demonstration, we build a surrogate for gravitational waveforms from eccentric binary black hole mergers. We show that providing the agent with a physics-informed domain ansatz substantially improves output model accuracy. The resulting analytic surrogate attains a median Advanced LIGO mismatch of $6.9\times10^{-4}$ together with an $\sim 8.4\times$ speedup in waveform evaluation, surpassing both symbolic regression and conventional machine learning baselines. Beyond producing an accurate model, the workflow identifies compact physical structure from the learned representation. As an astrophysical application, we use \texttt{GWAgent} to analyze the eccentricity of GW200129 and infer $e_{20\mathrm{Hz}}=0.099^{+0.063}_{-0.044}$. These results show that validation-constrained agentic workflows can produce accurate, fast, and interpretable surrogates for scientific simulations and inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11280 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves Islam, Tousif Wadekar, Digvijay Venumadhav, Tejaswi Zaldarriaga, Matias Mehta, Ajit Kumar Roulet, Javier Zackay, Barak General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena Artificial Intelligence Fast surrogate models for expensive simulations are now essential across the sciences, yet they typically operate as black boxes. We present \texttt{GWAgent}, a large language model (LLM)-based workflow that constructs interpretable analytic surrogates directly from simulation data. Surrogate modeling is well suited to agentic workflows because candidate models can be quantitatively validated against ground-truth simulations at each iteration. As a demonstration, we build a surrogate for gravitational waveforms from eccentric binary black hole mergers. We show that providing the agent with a physics-informed domain ansatz substantially improves output model accuracy. The resulting analytic surrogate attains a median Advanced LIGO mismatch of $6.9\times10^{-4}$ together with an $\sim 8.4\times$ speedup in waveform evaluation, surpassing both symbolic regression and conventional machine learning baselines. Beyond producing an accurate model, the workflow identifies compact physical structure from the learned representation. As an astrophysical application, we use \texttt{GWAgent} to analyze the eccentricity of GW200129 and infer $e_{20\mathrm{Hz}}=0.099^{+0.063}_{-0.044}$. These results show that validation-constrained agentic workflows can produce accurate, fast, and interpretable surrogates for scientific simulations and inference. |
| title | Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves |
| topic | General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena Artificial Intelligence |
| url | https://arxiv.org/abs/2605.11280 |