Adaptive Self-improvement LLM Agentic System for ML Library Development
This addresses the problem of automating ML library development for experts, but it appears incremental as it builds on existing LLM capabilities with a new system.
The paper tackles the challenge of generating high-performance ML libraries in architecture-specific programming languages (ASPLs) using LLMs, achieving up to 3.9x improvement over a baseline single LLM on a constructed benchmark.
ML libraries, often written in architecture-specific programming languages (ASPLs) that target domain-specific architectures, are key to efficient ML systems. However, writing these high-performance ML libraries is challenging because it requires expert knowledge of ML algorithms and the ASPL. Large language models (LLMs), on the other hand, have shown general coding capabilities. However, challenges remain when using LLMs for generating ML libraries using ASPLs because 1) this task is complicated even for experienced human programmers and 2) there are limited code examples because of the esoteric and evolving nature of ASPLs. Therefore, LLMs need complex reasoning with limited data in order to complete this task. To address these challenges, we introduce an adaptive self-improvement agentic system. In order to evaluate the effectiveness of our system, we construct a benchmark of a typical ML library and generate ASPL code with both open and closed-source LLMs on this benchmark. Our results show improvements of up to $3.9\times$ over a baseline single LLM.