Tag
KForge is a cross-platform framework that uses two collaborating LLM-based agents to automatically generate and optimize high-performance compute kernels for diverse AI accelerators, achieving significant speedups on NVIDIA B200 and Intel Arc B580 hardware.
This paper proposes Declarative Data Services (DDS), an architecture for structured agentic discovery of data-system compositions from declarative user intent. It decomposes the global search into bounded sub-searches and shows convergence on a trading-backend workload where unbounded discovery fails.
The paper introduces Kernel Discovery, an LLM-driven evolutionary framework for high-dimensional Bayesian optimization that searches a broader kernel space and achieves state-of-the-art results on benchmarks.
SMCEvolve introduces a principled framework for LLM-driven program evolution by reformulating it as sampling from a reward-tilted distribution using Sequential Monte Carlo. It provides convergence guarantees and outperforms existing methods across multiple scientific discovery benchmarks.
DataFlow is an LLM-driven framework for automated data preparation and workflow engineering, featuring nearly 200 reusable operators and six domain-general pipelines that improve LLM performance across tasks like math, code, and Text-to-SQL.