Who Wrote This Paper? Autonomous Scientific Discovery for 3DGS Research

Reproducing a published 3DGS paper takes weeks of expert engineering before any extension can be proposed. Prior autonomous-research systems read papers, draft hypotheses, and write code, but suffer from limited template length, executability, and traceability. Specifically, none has been demonstrated end-to-end in a live computer-vision subfield with intense activity. GS-Scientist is an autonomous research system for 3D Gaussian Splatting that addresses these limitations. Given a research prompt, a target-paper URL, or no input at all, it reproduces a published baseline, proposes an extension, trains and ablates across Mip-NeRF 360 and LLFF, writes the manuscript, and binds every reported number to a logged training run. Five design choices distinguish it: (i)candidates mutate plugins from a verified-reproduction backbone matched to published baselines; (ii)a cascade-weighted Elo tournament across eight islands scores on measured GPU PSNR with verbal-gradient feedback; (iii)a standing falsifier subtracts Elo on failure, integrating stress-test survival into selection; (iv)every reported number is bound to a logged training run, and the run cannot terminate while any claim is unbacked; (v)a seven-category 3DGS taxonomy wraps EVOLVE-BLOCK markers in domain-aligned scaffolds transferable across 3DGS repositories. GS-Scientist produces manuscripts that beat their reproduced target by $+0.18$ to $+3.78$ dB PSNR, including $+3.78$ dB on astrophotographic nebula rendering, for which no prior 3DGS method exists. The research cycle compresses from months of graduate-student time to days of mostly autonomous compute. Code, all manuscripts, experiment ledgers, and the cross-run paper store will be released.