Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more difficult. Off-the-shelf compilers can provide useful feedback post-generation, but does not guide intermediate generation steps, such as those during autoregressive LLM decoding. Constrained decoding intervenes earlier by rejecting invalid tokens during sampling, but requires white-box model access and costly reimplementation for semantic constraints.We introduce generative compilation, the first approach to obtaining compiler feedback on partial pr
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Introduction to Compilers and Language Design →
- FuzzySimilar title/name (fuzzy) · 84%GoogleCloudPlatform/generative-ai →
“Fuzzy title match (0.92): “Generative Compilation: On-the-Fly Compiler Feedback as AI G” ≈ “GoogleCloudPlatform/generative-ai””
- LinkedLinked via arxiv author · 85%Niels Mündler-Sasahara →
“Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code”
- LinkedLinked via arxiv author · 85%Hristo Venev →
“Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code”
- LinkedLinked via arxiv author · 85%Dawn Song →
“Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code”
- LinkedLinked via arxiv author · 85%Martin Vechev →
“Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code”
- LinkedLinked via arxiv author · 85%Jingxuan He →
“Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code”