SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2511.19635 · NeurIPS · 2025

Agint: Agentic Graph Compilation for Software Engineering Agents

Abhi Chivukula, Jay Somasundaram, Vijay Somasundaram

arXiv · PDF · Open in the Atlas

Code that ran

4 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 8 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2511.19635.json · badge: /api/ran/2511.19635.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
AgintHub/nifty-wilson canonical (classifier label)
classifier basis: census
4 ran · 8 no recorded run
FunctionStatusWhere it lives
allocate_resources Ran
ran; our contract draft was wrong, not the code
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/allocate_resources.py
pointer only (licence: NONE) · get_code("1fb88277b9afa355")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_vocabulary Ran
ran; our contract draft was wrong, not the code
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/create_vocabulary.py
pointer only (licence: NONE) · get_code("9dba977fb437a8af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_model Ran
ran; our contract draft was wrong, not the code
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/evaluate_model.py
pointer only (licence: NONE) · get_code("4f3f15762881b44c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

fine_tune_model Ran
ran; our contract draft was wrong, not the code
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/fine_tune_model.py
pointer only (licence: NONE) · get_code("287b9e16a2b4cf3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

define_core_trading_philosophy Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/build_jane_street/code/define_core_trading_philosophy.py
pointer only (licence: NONE) · get_code("8bd4458bcb467a91")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

define_model_architecture Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/define_model_architecture.py
pointer only (licence: NONE) · get_code("5df22a47a8759b0a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

initialize_model_weights Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/initialize_model_weights.py
pointer only (licence: NONE) · get_code("a40a440de9841f5c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_configuration Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/load_configuration.py
pointer only (licence: NONE) · get_code("0e3510f90b73c5a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

prepare_training_data Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/prepare_training_data.py
pointer only (licence: NONE) · get_code("4e63e0fb6e7200b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

setup_environment Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/setup_environment.py
pointer only (licence: NONE) · get_code("e16a0e38c43a7ae3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

split_data Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/split_data.py
pointer only (licence: NONE) · get_code("88827d606930eb54")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

tokenize_data Not yet run
unverified (harvested, no recorded run)
AgintHub/nifty-wilson/outputs/dagify/train_large_language_model/code/tokenize_data.py
pointer only (licence: NONE) · get_code("e6eb857d2fdd36c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AgintHub/nifty-wilson when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 (Directed Acyclic Graphs). Agint introduces explicit type floors (TEXT → TYPED → SPEC → CODE) grounded in semantic graph transformations and a hybrid LLM/function JIT runtime, enabling dynamic graph refinement, reproducible and optimizable execution, speculative evaluation, and interoperability with existing developer tools. Agint's typed graph bindings ensure reliability and enable concurrent composition of codebases by construction, supporting accelerated development using smaller, faster models for lower latency, more efficient context use, and higher throughput. Hierarchical compilation allows scalable graph edits, while the graph structure provides 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 leverage Agint Flow GUI with visual editing, conversational refinement, and debugging to promote prototype agentic workflows to production code. This continuous cocreation model lets teams 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2511.19635")
get_code_for_paper("2511.19635")
have("2511.19635")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2511.19635.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2511.19635.svg)](https://syntology.ai/paper/2511.19635)

Connect an agent — have() is free.