SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02412 · 2024

LLM Augmented LLMs: Expanding Capabilities through Composition

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 2 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2401.02412.json · badge: /api/ran/2401.02412.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
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
lucidrains/CALM-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
log Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from lucidrains/speculative-decoding
pointer only · get_code("b5472673332de78e")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

SequenceOf Ran
ran; our contract draft was wrong, not the code
lucidrains/CALM-pytorch/CALM_pytorch/CALM.py
code served (permissive licence) · get_code("4b7e919dc74f8327")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned UnionType. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from typing import Union

torch.manual_seed(0)

# SequenceOf is a type alias that represents either a tuple or list of type t
# The function takes a type parameter 't' and returns a union type

# For this function, we need to provide a type as the argument
# Let's use a simple type like int or str

ARGS = {
    't': int
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type UnionType — a UnionType output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a UnionType output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
SingularOrMany Ran
ran; our contract draft was wrong, not the code
lucidrains/CALM-pytorch/CALM_pytorch/CALM.py
code served (permissive licence) · get_code("074a76082c6cda9b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned UnionType. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from typing import Union

torch.manual_seed(0)

# The function SingularOrMany(t) is a type hint that returns either:
# - a single instance of type t
# - OR a SequenceOf(t), which is tuple[t, ...] | list[t]

# Since this is a type hint function, we need to demonstrate what valid
# arguments would be. The parameter 't' is a type.

# Let's create some example types to pass
class SimpleClass:
    def __init__(self, value):
        self.value = value

class AnotherClass:
    def __init__(self, name):
        self.name = name

# Create instances that would be valid returns from SingularOrMany
single_int = 42
sequence_of_ints = [1, 2, 3]
sequence_of_ints_tuple = (10, 20, 30)

single_tensor = torch.randn(2, 4)
sequence_of_tensors = [torch.randn(2, 4), torch.randn(2, 4)]
sequence_of_tensors_tuple = (torch.randn(2, 4), torch.randn(2, 4))

single_obj = SimpleClass(100)
sequence_of_objs = [SimpleClass(1), SimpleClass(2)]
sequence_of_objs_tuple = (SimpleClass(10), SimpleClass(20))

# The function takes parameter 't' which is a type
# Valid arguments would be type objects
ARGS = {
    "t": int
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type UnionType — a UnionType output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a UnionType output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
default Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/gradnorm-pytorch
pointer only · get_code("99b3563ebc6734ad")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

exists Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/gradnorm-pytorch
pointer only · get_code("b7c3487f192e31b7")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 2 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.

FunctionAlso present inEarliest-datedOthers named
exists 27 other papers
9 dated earlier, 2 the same month, 15 later, 1 same year, order not determinable · 3 only as an assembly brick
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
2006.15055 (2020-06)
Object-Centric Learning with Slot Attention
2010.10241 (2020-10)
BYOL works even without batch statistics
and 24 more not named here
log 22 other papers
13 dated earlier, 1 the same month, 8 later · 9 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1907.05242 (2019-07)
Large Memory Layers with Product Keys
2203.07852 (2022-03)
Block-Recurrent Transformers
and 19 more not named here
default 21 other papers
6 dated earlier, 2 the same month, 13 later · 1 only as an assembly brick
2006.15055 (2020-06)
Object-Centric Learning with Slot Attention
2110.00218 (2021-10)
On the Importance of Gradients for Detecting Distributional Shifts in the Wild
2309.02612 (2023-09)
Music Source Separation with Band-Split RoPE Transformer
and 18 more not named here

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

Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to augment them or impart new skills. On the other hand, due to their adaptation abilities, several new instances of these models are being trained towards new domains and tasks. In this work, we study the problem of efficient and practical composition of existing foundation models with more specific models to enable newer capabilities. To this end, we propose CALM -- Composition to Augment Language Models -- which introduces cross-attention between models to compose their representations and enable new capabilities. Salient features of CALM are: (i) Scales up LLMs on new tasks by 're-using' existing LLMs along with a few additional parameters and data, (ii) Existing model weights are kept intact, and hence preserves existing capabilities, and (iii) Applies to diverse domains and settings. We illustrate that augmenting PaLM2-S with a smaller model trained on low-resource languages results in an absolute improvement of up to 13\% on tasks like translation into English and arithmetic reasoning for low-resource languages. Similarly, when PaLM2-S is augmented with a code-specific model, we see a relative improvement of 40\% over the base model for code generation and explanation tasks -- on-par with fully fine-tuned counterparts.

For agents

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

get_harvested_code_for_paper("2401.02412")
get_code_for_paper("2401.02412")
have("2401.02412")

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

curl https://syntology.ai/api/ran/2401.02412.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.02412.svg)](https://syntology.ai/paper/2401.02412)

Connect an agent — have() is free.