Agint: Agentic Graph Compilation for Software Engineering Agents
Abhi Chivukula, Jay Somasundaram, Vijay Somasundaram

TL;DR
Agint introduces an agentic graph compiler and runtime that transforms natural language instructions into effect-aware code DAGs, enhancing reliability, scalability, and developer productivity in AI-assisted coding.
Contribution
It presents a novel hierarchical, effect-aware graph compilation approach with explicit type floors, enabling dynamic refinement, reproducibility, and interoperability for coding agents.
Findings
Improves reliability through typed graph bindings.
Enables scalable, concurrent codebase composition.
Supports low-latency, high-throughput code generation.
Abstract
LLM-based coding agents are increasingly common but still face challenges in context management, latency, reliability, reproducibility, and scalability. We present Agint, an agentic graph compiler, interpreter, and runtime that incrementally and hierarchically converts natural-language instructions into typed, effect-aware code DAGs. Agint introduces explicit type floors (text to data to spec to code) grounded in semantic graph transformations and a hybrid LLM and function-based JIT runtime. This enables dynamic graph refinement, reproducible and optimizable execution, speculative evaluation, and interoperability with existing developer tools. Agint's typed graph bindings improve reliability and allow concurrent composition of concurrent codebases by construction, supporting accelerated development with smaller and faster models, lower latency, efficient context utilization, and higher…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsModel-Driven Software Engineering Techniques · Graph Theory and Algorithms · Multi-Agent Systems and Negotiation
