A GLIMPSE of the 99%: a census of the faintest galaxies during the epoch of reionization and its implications for galaxy formation models

We present a comprehensive study of the galaxy UV luminosity function (UVLF) at $z=6-9$ leveraging deep JWST observations from the GLIMPSE survey. Thanks to gravitational lensing, we probe the UVLF to an unprecedented depth of $M_{\text{UV}} = -12$ mag, approximately three magnitudes deeper than previous robust constraints. Our UVLF determination incorporates a rigorous end-to-end uncertainty framework, including statistical and systematic lensing uncertainties. We find that the $z \sim 7$ UVLF continues to rise steeply with a faint-end slope of $α= -1.98_{-0.05}^{+0.06}$. Crucially, our data show no clear evidence of a turnover down to \muv $= -12.3$. The persistence of this faint population provides stringent constraints on galaxy formation models and cosmological simulations that predict an early flattening of the luminosity function due to radiative feedback or star-formation thresholds. Furthermore, post-JWST models specifically calibrated to match the UV-bright excess at $z > 10$ generally fail to reproduce the observed evolution toward lower redshifts and fainter magnitudes, highlighting a significant tension in our current understanding of early galaxy assembly. We derive a comoving ionizing emissivity at $z=7$ of log($n_{\mathrm ion}$ / s${\mathstrut}^{-1}$ Mpc${\mathstrut}^{-3}$) $\approx 50.85$, which suggests that faint galaxies dominate the ionizing budget, providing enough photons to maintain reionization even in a highly clumped IGM ($C_{\text{HII}} = 5$). As our detection of faint galaxies effectively rules out a luminosity function truncation at $M_{\text{UV}} \geq -15$, these results emphasize the need to either accurately characterize the ionizing properties of the global, low-mass galaxy population at $z > 6$, or to refine physical models of intergalactic medium clumping and its redshift evolution to maintain consistency with the observed reionization timeline.