All topics
#Code Generation
Three entries on this site carry the Code Generation tag: three papers, dated 2026.
Papers
-
Test-Input Generation for Tensor Programs: What Actually Finds Kernel Bugs
Paper · 2026 · arXiv · cited by 0 Companion paper to the Correctness Illusion. We study what kinds of test inputs actually find bugs in LLM-generated GPU kernels. Existing benchmarks (KernelBench) use uniformly-sampled inputs. -
The Correctness Illusion in LLM-Generated GPU Kernels
Paper · 2026 · arXiv · cited by 0 LLM-generated GPU kernels pass the standard correctness test and are still wrong. We present the Correctness Illusion: the standard test bed for LLM-generated GPU kernels (KernelBench) under-specifies the input distribution, leading to kernels that pass the. -
Before the Pull Request: Mining Multi-Agent Coordination
Paper · 2026 · arXiv · cited by 0 Multi-agent coding is the new inner loop. Five agents converging on a single correct solution is the new test of orchestration.