Nanopass Framework: Clean Compiler Creation Language
Summary
Nanopass Framework is a domain-specific language embedded in Scheme for creating compilers through small passes and intermediate representations, reducing boilerplate and improving maintainability.
View Cached Full Text
Cached at: 04/20/26, 02:55 PM
Similar Articles
PassNet: Scaling Large Language Models for Graph Compiler Pass Generation
This paper introduces PassNet, a large-scale ecosystem for LLM-based compiler pass generation, including a dataset of over 18K computational graphs and a benchmark (PassBench) with a new metric. Experiments reveal that while LLMs can achieve up to 3x speedup over TorchInductor on individual subgraphs, consistency remains a bottleneck; fine-tuning a small model on PassNet trajectories yields significant improvements.
CPPL: A Circuit Prompt Programming Language
CPPL is a compiler-mediated framework that bridges LLMs and hardware design by using a Python DSL and JSON-based intermediate representation to enable statically checkable, optimizable RTL generation.
CohereLabs/North-Mini-Code-1.0
Cohere Labs released North Mini Code, a 30B-parameter (3B active) open-weights model optimized for code generation, agentic software engineering, and terminal tasks, licensed under Apache 2.0.
DeepCode: Open Agentic Coding
DeepCode is a fully autonomous framework for document-to-codebase synthesis that uses principled information-flow management to convert scientific papers into production-grade code, achieving state-of-the-art results on PaperBench and surpassing PhD-level human experts.
FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines
FAPO is a framework for fully autonomous prompt optimization of multi-step LLM pipelines, combining prompt editing and structural changes. It outperforms the GEPA baseline in 15 of 18 comparisons, with gains up to +33.8 pp on security tasks.