IntelligenceLab/Long-Horizon-Terminal-Bench Benchmark • Updated about 20 hours ago • 154 • 26.4k • 140
Self-Supervised Scaling of Terminal Environments for Scientific Domains Paper • 2610.02710 • Published 11 days ago • 13
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite Paper • 2610.02826 • Published 11 days ago • 103
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders Paper • 2609.31620 • Published 18 days ago • 145