# Shedding Light on Dark Matter at the LHC with Machine Learning

arXiv: https://arxiv.org/abs/2509.15121 · HTML: https://mlsanity.com/paper/2509.15121/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 151 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [A high-bias, low-variance introduction to Machine Learning for physicists](https://mlsanity.com/paper/1803.08823/) (2018)
- [A Living Review of Machine Learning for Particle Physics](https://mlsanity.com/paper/2102.02770/) (2021)
- [Machine Learning in High Energy Physics Community White Paper](https://mlsanity.com/paper/1807.02876/) (2018)
- [Machine Learning for Anomaly Detection in Particle Physics](https://mlsanity.com/paper/2312.14190/) (2023)
- [Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning](https://mlsanity.com/paper/2209.07559/) (2022)
- [Machine-Learned Exclusion Limits without Binning](https://mlsanity.com/paper/2211.04806/) (2022)
- [Machine-Learning Analysis of Radiative Decays to Dark Matter at the LHC](https://mlsanity.com/paper/2410.13799/) (2024)

## Abstract (arXiv)

We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the Z3-symmetric Next-to-Minimal Supersymmetric Standard Model (NMSSM). This framework gives rise to regions of parameter space where DM is obtained via co-annihilation with nearby higgsino-like electroweakinos and DM direct detection~signals are suppressed, the so-called ``blind spots''. On the other hand, collider signatures remain promising due to enhanced radiative decay modes of higgsinos into the singlino-dominated LSP and photons, rather than into leptons or hadrons. Compared to MSSM scenarios with light bino- and wino-like electroweakinos, the NMSSM allows for final states with multiple photons arising from cascade radiative decays, providing a distinctive collider signature. This motivates searches for radiatively decaying neutralinos, however, these signals face substantial background challenges, as the decay products are typically soft due to the small mass-splits (Delta m) between the LSP and the higgsino-like coannihilation partners. We apply a data-driven Machine Learning (ML) analysis that improves sensitivity to these subtle signals, offering a powerful complement to traditional search strategies to discover a new physics scenario. Using an LHC integrated luminosity of 100~fb-1 at 14~TeV, the method achieves a 5σ discovery reach for higgsino masses up to 225~GeV with Delta m!lesssim!12~GeV, and a 2σ exclusion up to 285~GeV with Delta m!lesssim!20~GeV. These results highlight~the power of collider searches to probe DM candidates that remain hidden from current~direct detection experiments, and provide a motivation for a search by the LHC collaborations using ML methods.