SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.15079 · ICLR · 2025

GOAL: A Generalist Combinatorial Optimization Agent Learner

Darko Drakulic, Sofia Michel, Jean-Marc Andreoli

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 4 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2406.15079.json · badge: /api/ran/2406.15079.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
naver/goal-co canonical (classifier label)
classifier basis: classifier_2025
4 ran · 3 no recorded run
FunctionStatusWhere it lives
MultiHeadAttention Ran
ran on a synthesized input
naver/goal-co/model/goal.py
pointer only (licence: NOASSERTION) · get_code("2bd36da6a44d602c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver/goal-co (NOASSERTION). 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.

NodeAdapter Ran
ran on a synthesized input
naver/goal-co/model/goal.py
pointer only (licence: NOASSERTION) · get_code("87c3247476434eba")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver/goal-co (NOASSERTION). 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.

OutputAdapter Ran
ran on a synthesized input
naver/goal-co/model/goal.py
pointer only (licence: NOASSERTION) · get_code("fdff959b3c32f2c8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver/goal-co (NOASSERTION). 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.

ResidualNorm Ran
ran on a synthesized input
naver/goal-co/model/goal.py
pointer only (licence: NOASSERTION) · get_code("fdfed8c3091101c8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver/goal-co (NOASSERTION). 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.

EdgeAdapter Not yet run
unverified (harvested, no recorded run)
naver/goal-co/model/goal.py
pointer only (licence: NOASSERTION) · get_code("e9ed6e57077edb7d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver/goal-co (NOASSERTION). 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.

GOAL Not yet run
unverified (harvested, no recorded run)
naver/goal-co/model/goal.py
pointer only (licence: NOASSERTION) · get_code("86fb44a114d5d930")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver/goal-co (NOASSERTION). 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.

Layer Not yet run
unverified (harvested, no recorded run)
naver/goal-co/model/goal.py
pointer only (licence: NOASSERTION) · get_code("e25d388b98c8e3f0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, naver/goal-co (NOASSERTION). 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Machine Learning-based heuristics have recently shown impressive performance in solving a variety of hard combinatorial optimization problems (COPs). However they generally rely on a separate neural model, specialized and trained for each single problem. Any variation of a problem requires adjustment of its model and re-training from scratch. In this paper, we propose GOAL (for Generalist combinatorial Optimization Agent Learner), a generalist model capable of efficiently solving multiple COPs and which can be fine-tuned to solve new COPs. GOAL consists of a single backbone plus light-weight problem-specific adapters for input and output processing. The backbone is based on a new form of mixed-attention blocks which allows to handle problems defined on graphs with arbitrary combinations of node, edge and instance-level features. Additionally, problems which involve heterogeneous types of nodes or edges are handled through a novel multi-type transformer architecture, where the attention blocks are duplicated to attend the meaningful combinations of types while relying on the same shared parameters. We train GOAL on a set of routing, scheduling and classic graph problems and show that it is only slightly inferior to the specialized baselines while being the first multi-task model that solves a wide range of COPs. Finally we showcase the strong transfer learning capacity of GOAL by fine-tuning it on several new problems. Our code is available at this url.

For agents

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

get_harvested_code_for_paper("2406.15079")
get_code_for_paper("2406.15079")
have("2406.15079")

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

curl https://syntology.ai/api/ran/2406.15079.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.15079.svg)](https://syntology.ai/paper/2406.15079)

Connect an agent — have() is free.