SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.16667 · EMNLP · 2024

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation

Maosong Sun, Zhiyuan Liu, Yankai Lin, Yining Ye, Yujia Qin, Zhong Zhang, Yesai Wu, Shihao Liang, Yaxi Lu, Qinyu Luo, Yingli Zhang, Xiaoyin Che, and 1 more

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/2402.16667.json · badge: /api/ran/2402.16667.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
OpenBMB/RepoAgent canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
Significant-Gravitas/AutoGPT canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
is_markdown_file Ran
ran; our contract draft was wrong, not the code
OpenBMB/RepoAgent/display/book_tools/generate_summary_from_book.py
code served (permissive licence) · get_code("93468904995ed5bf")
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, through the batch API) and returned str. 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 re

def is_markdown_file(filename):
    match = re.search('.md$|.markdown$', filename)
    if not match:
        return False
    elif len(match.group()) is len('.md'):
        return filename[:-3]
    elif len(match.group()) is len('.markdown'):
        return filename[:-9]

ARGS = {
    'filename': 'document.md'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
markdown_file_in_dir Ran
ran, violated the contract we drafted
OpenBMB/RepoAgent/display/book_tools/generate_summary_from_book.py
code served (permissive licence) · get_code("56ebe798c9a93995")
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, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 os
import re
import tempfile

# Create a temporary directory with markdown files for testing
temp_dir = tempfile.mkdtemp()

# Create a subdirectory
subdir = os.path.join(temp_dir, "subdir")
os.makedirs(subdir, exist_ok=True)

# Create a markdown file
md_file = os.path.join(subdir, "test.md")
with open(md_file, 'w') as f:
    f.write("# Test Markdown\n")

ARGS = {
    "dire": temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
validate_public_url Ran
ran; our contract draft was wrong, not the code
Significant-Gravitas/AutoGPT/autogpt_platform/single-container/runtime_config.py
pointer only (licence: NOASSERTION) · get_code("b1e26581a38df263")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Significant-Gravitas/AutoGPT (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.

ensure_runtime_config Not yet run
unverified (harvested, no recorded run)
Significant-Gravitas/AutoGPT/autogpt_platform/single-container/runtime_config.py
pointer only (licence: NOASSERTION) · get_code("5c9729114d117fe9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Significant-Gravitas/AutoGPT (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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging. However, their utilization in the domain of code documentation generation remains underexplored. To this end, we introduce REPOAGENT, a large language model powered open-source framework aimed at proactively generating, maintaining, and updating code documentation. Through both qualitative and quantitative evaluations, we have validated the effectiveness of our approach, showing that REPOAGENT excels in generating highquality repository-level documentation. The code and results are publicly accessible at https://github.com/OpenBMB/RepoAgent.

For agents

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

get_harvested_code_for_paper("2402.16667")
get_code_for_paper("2402.16667")
have("2402.16667")

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

curl https://syntology.ai/api/ran/2402.16667.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.16667.svg)](https://syntology.ai/paper/2402.16667)

Connect an agent — have() is free.