# Agint: Agentic Graph Compilation for Software Engineering Agents

arXiv: https://arxiv.org/abs/2511.19635 · HTML: https://mlsanity.com/paper/2511.19635/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 21 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions](https://mlsanity.com/paper/2410.20424/) (2024)
- [ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code](https://mlsanity.com/paper/2311.09835/) (2023)
- [CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules](https://mlsanity.com/paper/2310.08992/) (2023)
- [MASAI: Modular Architecture for Software-engineering AI Agents](https://mlsanity.com/paper/2406.11638/) (2024)
- [Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents](https://mlsanity.com/paper/2408.07060/) (2024)
- [Type-Constrained Code Generation with Language Models](https://mlsanity.com/paper/2504.09246/) (2025)
- [QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checks](https://mlsanity.com/paper/2501.17167/) (2025)
- [Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation](https://mlsanity.com/paper/2405.20092/) (2024)
- [Toward Trustworthy Neural Program Synthesis](https://mlsanity.com/paper/2210.00848/) (2022)
- [Challenges and Paths Towards AI for Software Engineering](https://mlsanity.com/paper/2503.22625/) (2025)
- [Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model](https://mlsanity.com/paper/2503.08738/) (2025)

## Built on by (most cited first, 4 of 4)

- [Natural-Language Agent Harnesses](https://mlsanity.com/paper/2603.25723/) (2026)
- [Securing LLM Agents Need Intent-to-Execution Integrity](https://mlsanity.com/paper/2605.16976/) (2026)
- [λA: A Typed Lambda Calculus for LLM Agent Composition](https://mlsanity.com/paper/2604.11767/) (2026)
- [Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer](https://mlsanity.com/paper/2604.17883/) (2026)

## Abstract (arXiv)

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 throughput. Hierarchical compilation allows scalable graph edits, while the graph structure supports reproducibility and efficient parallel generation. Agint provides a composable unix-style toolchain: dagify (DAG compiler), dagent (hybrid JIT runtime), schemagin (schema generator), and datagin (data transformer) for realtime, low-latency code and dataflow creation. Human developers and coding agents refine graphs through the Agint CLI, while non-technical users use Agint Flow GUI for visual editing, conversational refinement, and debugging to promote prototype agentic workflows to production code. This continuous co-creation model allows teams to prototype quickly, refine seamlessly, and deploy reliably, bridging natural language, compiler methods, and developer tooling to enable a new generation of composable, team-centric coding agents at scale.