Atomic receivers that use Rydberg vapor cells to sense electromagnetic fields offer a promising alternative to conventional radio-frequency front-ends. In multi-antenna configurations , the magnitude-only, phase-insensitive measurements produced by atomic receivers pose challenges for traditional detection methods. Existing solutions rely on two-step iterative optimization that suffers from cascaded channel-estimation errors and high computational complexity. We propose a channel-state-information (CSI)-free symbol-detection method based on in-context learning (ICL) that directly maps pilot-response pairs to data-symbol predictions without explicit channel estimation. Simulations show that ICL achieves competitive accuracy with higher computational efficiency than existing approaches.