Toward Autonomous Radio Follow-up of Multi-messenger Transients with RADAR: From Alert Parsing to Inference and Observation Scheduling
Abstract
Multi-messenger astronomy (MMA), the joint study of cosmic sources through gravitational waves (GWs), electromagnetic (EM) radiation, neutrinos, and cosmic rays, is rapidly reshaping time-domain astrophysics. Realizing the promise of MMA will require coordinating heterogeneous observing resources and automating the chain from alert to analysis to follow-up. RADAR (Radio Afterglow Detection and AI-driven Response) is a federated, privacy-enhancing framework for the radio follow-up of GW events, previously validated on GW170817. Here, we extend it along three axes. First, we benchmark three large language models (LLMs; GPT-5.5, Claude-Opus-4.7, and Gemini-3.5-Flash) against the GW170817 radio light curve dataset. GPT-5.5 attains the highest event-level F1 score, the harmonic mean of precision and recall, at 0.893 ± 0.010, and the highest GCN-level recall, 0.794 ± 0.013, improving on previous GPT-4.1 results by 16\% and 10\%, respectively, while Claude-Opus-4.7 achieves the highest precision, 0.978 ± 0.014. Second, we introduce concurrent likelihood evaluation, which speeds up the MCMC computation by a factor of 40× over our previous results. Third, we present an LLM-driven scheme that converts natural-language observing requests into submission-ready scheduling blocks for the Karl G. Jansky Very Large Array. Together, these developments advance RADAR toward a scalable, largely autonomous system for GW radio follow up.
Related
- A new model for the continuum spectra of AM CVn binaries and multi-messenger inference with normalizing flows
- Multi-messenger and multi-band signal from first-order phase transitions in proto-neutron stars
- Models of spectral bumps of primary cosmic rays and multi-messenger tests
- Circumbinary discs as the origin of circumstellar material around interacting H-poor supernovae and fast blue optical transients
- Radio emission from radio-bright fast blue optical transients powered by trans-relativistic shocks in confined circumstellar material
BibTeX
@misc{hateganmarandiuc2026toward,
title = {{Toward Autonomous Radio Follow-up of Multi-messenger Transients with RADAR: From Alert Parsing to Inference and Observation Scheduling}},
author = {Mihael Hategan-Marandiuc and Tanner O'Dwyer and Alessandra Corsi and Eliu Huerta and Zilinghan Li and Ian T. Foster and Kyle Chard and Ryan Chard and Amal Gueroudji},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18233},
eprint = {2609.18233},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18233},
}
RIS
TY - UNPB
TI - Toward Autonomous Radio Follow-up of Multi-messenger Transients with RADAR: From Alert Parsing to Inference and Observation Scheduling
AU - Mihael Hategan-Marandiuc
AU - Tanner O'Dwyer
AU - Alessandra Corsi
AU - Eliu Huerta
AU - Zilinghan Li
AU - Ian T. Foster
AU - Kyle Chard
AU - Ryan Chard
AU - Amal Gueroudji
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18233
UR - https://arxiv.org/abs/2609.18233
AB - Multi-messenger astronomy (MMA), the joint study of cosmic sources through gravitational waves (GWs), electromagnetic (EM) radiation, neutrinos, and cosmic rays, is rapidly reshaping time-domain astrophysics. Realizing the promise of MMA will require coordinating heterogeneous observing resources and automating the chain from alert to analysis to follow-up. RADAR (Radio Afterglow Detection and AI-driven Response) is a federated, privacy-enhancing framework for the radio follow-up of GW events, previously validated on GW170817. Here, we extend it along three axes. First, we benchmark three large language models (LLMs; GPT-5.5, Claude-Opus-4.7, and Gemini-3.5-Flash) against the GW170817 radio light curve dataset. GPT-5.5 attains the highest event-level F_1 score, the harmonic mean of precision and recall, at 0.893 ± 0.010, and the highest GCN-level recall, 0.794 ± 0.013, improving on previous GPT-4.1 results by 16\% and 10\%, respectively, while Claude-Opus-4.7 achieves the highest precision, 0.978 ± 0.014. Second, we introduce concurrent likelihood evaluation, which speeds up the MCMC computation by a factor of 40× over our previous results. Third, we present an LLM-driven scheme that converts natural-language observing requests into submission-ready scheduling blocks for the Karl G. Jansky Very Large Array. Together, these developments advance RADAR toward a scalable, largely autonomous system for GW radio follow up.
ER -