T2J-BENCH is introduced, a benchmark of 63 whole-repository PyTorch-to-JAX migration tasks spanning 18 model families across both training and serving, and TWINHARNESS, a reference-grounded agent harness that turns the agent's executable PyTorch source into legitimate self-verification feedback.
Tao Feng, Jie-Feng Chen, Lin-Xin Song et al.· 0 citations
DuoDiscover enables autonomous optimization from software to chip architecture, and surpasses both AlphaEvolve-based ArchAgent v2 and the best human design, with 1.65 times the gain on a CPU microarchitecture optimization task with evaluations of up to 28 hours.
Shubham Agarwal, Akshat Gupta, M. Heddes et al.· 0 citations
It is shown that explicit idea-level allocation makes semantic coverage directly controllable, and that broader coverage becomes increasingly valuable when competitive research directions are sparse among many plausible alternatives.