Tag
The paper introduces GRAFT, an execution-guided genetic recombination method for automated LLM agent design that uses parent-specific execution evidence to guide semantic crossover, achieving 82.0% mean test accuracy across six reasoning and programming settings—9.8 points above the strongest baseline.
A technical analysis of optimizing LLM inference using agent fleets, based on DeepSeek 4.1 Flash optimization reaching 2300 tok/s, highlighting that most gains come from configs/graphs rather than new kernels, questioning megakernel approaches, and emphasizing verification and convergence in automated optimization runs.
This paper presents an automated tensor scheduling approach for hybrid CPU-GPU LLM inference on consumer devices.