Skip to main content

# Autonomous Scientific Discovery

2 related articles

Subscribe to updates

arXiv Nov 10, 2026
Scientific agents stop leaning on the last round: Sage-Taiyi keeps what it learns mid-search and tops Taiyi-Bench at 54.0
Sage-Taiyi splits scientific discovery into two levels: an object level that searches over a target tree and an idea graph, and a meta level that keeps a revisable cognitive state recording which judgments have evidence and which premises remain untested, then uses it to decide what to investigate next and which method to apply. On Taiyi-Bench, 265 tasks drawn from 50 papers across ten disciplines, it scores 54.0 overall against 47.9 for the strongest baseline, AI Scientist-v2, ranking first on all eight metrics. Five expert-guided collaborations in chemistry, materials and engineering carried some proposals to experimental or computational validation, including a cobalt-catalysed carbonylation model reaction raised from trace amounts to 84% yield.
Sage-Taiyi splits scientific discovery into two levels: an object level that searches over a target tree and an idea graph, and a meta level that keeps a revisable cognitive state recording which judgments have evidence and which premises remain untested, then uses it to decide what to investigate next and which method to apply. On Taiyi-Bench, 265 tasks drawn from 50 papers across ten disciplines, it scores 54.0 overall against 47.9 for the strongest baseline, AI Scientist-v2, ranking first on all eight metrics. Five expert-guided collaborations in chemistry, materials and engineering carried some proposals to experimental or computational validation, including a cobalt-catalysed carbonylation model reaction raised from trace amounts to 84% yield.
Weida Wang（First author）
Sage-Taiyi Scientific Discovery Taiyi-Bench Autonomous Scientific Discovery
arXiv Oct 22, 2026
3D Gaussian Splatting research without hand-written code: SplatLab runs from a one-line prompt to a manuscript, each beating its reproduced baseline
SplatLab hands the 3D Gaussian Splatting research loop to 36 agents: it reproduces a published baseline, mutates a verified plugin, trains, ablates and writes a manuscript, binding every reported number to a logged GPU run. On Mip-NeRF 360 and LLFF its manuscripts beat their reproduced targets on PSNR; on astrophotographic nebula rendering, where no prior 3DGS method exists, Nebula3DGS-v2 raises PSNR from the 3DGS baseline's 32.58 dB to 36.36 dB.
SplatLab hands the 3D Gaussian Splatting research loop to 36 agents: it reproduces a published baseline, mutates a verified plugin, trains, ablates and writes a manuscript, binding every reported number to a logged GPU run. On Mip-NeRF 360 and LLFF its manuscripts beat their reproduced targets on PSNR; on astrophotographic nebula rendering, where no prior 3DGS method exists, Nebula3DGS-v2 raises PSNR from the 3DGS baseline's 32.58 dB to 36.36 dB.
Seemandhar Jain（First author）
SplatLab Autonomous Scientific Discovery Gaussian Splatting Verified-Reproduction Backbone

You’re all caught up