AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918453069217792 |
|---|---|
| author | Du, Weihua Zhuo, Jingming Dong, Yixin He, Andre Wang Sun, Weiwei Zheng, Zeyu Karunaratne, Manupa Fox, Ivan Dettmers, Tim Chen, Tianqi Yang, Yiming Welleck, Sean |
| author_facet | Du, Weihua Zhuo, Jingming Dong, Yixin He, Andre Wang Sun, Weiwei Zheng, Zeyu Karunaratne, Manupa Fox, Ivan Dettmers, Tim Chen, Tianqi Yang, Yiming Welleck, Sean |
| contents | Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improvement remains far from solved: most approaches still treat each problem instance independently, without accumulating reusable knowledge. This limitation is particularly pronounced in domain-specific languages such as Triton, which are underrepresented in LLM pretraining data. Their strict constraints and non-linear optimization landscape further make naive generation and local refinement unreliable. We propose AdaExplore, an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation through two complementary stages: failure-driven adaptation and diversity-preserving search, jointly improving correctness and optimization performance without additional fine-tuning or external knowledge. In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules, helping subsequent generations remain within the feasible set. In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration, allowing it to explore the optimization landscape beyond local optima. Experiments on kernel runtime optimization benchmarks validate these gains: AdaExplore achieves 3.12x and 1.72x speedups on KernelBench Level-2 and Level-3, respectively, within 100 steps, and continues to improve with additional computation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16625 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation Du, Weihua Zhuo, Jingming Dong, Yixin He, Andre Wang Sun, Weiwei Zheng, Zeyu Karunaratne, Manupa Fox, Ivan Dettmers, Tim Chen, Tianqi Yang, Yiming Welleck, Sean Computation and Language Artificial Intelligence Machine Learning Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improvement remains far from solved: most approaches still treat each problem instance independently, without accumulating reusable knowledge. This limitation is particularly pronounced in domain-specific languages such as Triton, which are underrepresented in LLM pretraining data. Their strict constraints and non-linear optimization landscape further make naive generation and local refinement unreliable. We propose AdaExplore, an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation through two complementary stages: failure-driven adaptation and diversity-preserving search, jointly improving correctness and optimization performance without additional fine-tuning or external knowledge. In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules, helping subsequent generations remain within the feasible set. In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration, allowing it to explore the optimization landscape beyond local optima. Experiments on kernel runtime optimization benchmarks validate these gains: AdaExplore achieves 3.12x and 1.72x speedups on KernelBench Level-2 and Level-3, respectively, within 100 steps, and continues to improve with additional computation. |
| title | AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.16625 |