SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.00622 · 2024

Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement

arXiv · PDF · Open in the Atlas

Code that ran

10 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 2 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/2411.00622.json · badge: /api/ran/2411.00622.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
LingmaTongyi/Lingma-SWE-GPT canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
add_step_trigger Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/inference.py
pointer only (licence: NONE) · get_code("4a9d291fd8231065")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

count_and_organize_tasks Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/post_process.py
pointer only (licence: NONE) · get_code("4ba8180b0bea20ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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_new_logger Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/log.py
pointer only (licence: NONE) · get_code("b80e52761ce47d00")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

extract_gpt_content Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/model/gpt.py
pointer only (licence: NONE) · get_code("62d4bc6ae2e0bf70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

get_all_py_files Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/MCTS/SWEGPT/run_gpt_and_bm25.py
pointer only (licence: NONE) · get_code("fbc78031a9466729")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

get_bm25_score Ran
ran, honoured the contract we drafted
LingmaTongyi/Lingma-SWE-GPT/app/MCTS/SWEGPT/run_gpt_and_bm25.py
pointer only (licence: NONE) · get_code("52159cbb2c30cfe0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

get_logger Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/log.py
pointer only (licence: NONE) · get_code("48d86997cc5e93eb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

get_review_result Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/inference.py
pointer only (licence: NONE) · get_code("ff5fc9ba9b79f7a5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

prepare_issue_prompt Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/inference.py
pointer only (licence: NONE) · get_code("8509558455ad7ff9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

read_extract_status Ran
ran; our contract draft was wrong, not the code
LingmaTongyi/Lingma-SWE-GPT/app/post_process.py
pointer only (licence: NONE) · get_code("da242e87f1c615cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

chatswegpt Not yet run
unverified (harvested, no recorded run)
LingmaTongyi/Lingma-SWE-GPT/app/model/call_vllm.py
pointer only (licence: NONE) · get_code("c27aa88ac8371c88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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.

run_script_in_conda Not yet run
unverified (harvested, no recorded run)
LingmaTongyi/Lingma-SWE-GPT/app/utils.py
pointer only (licence: NONE) · get_code("5ab9d3877e545f78")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, LingmaTongyi/Lingma-SWE-GPT 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

Recent advancements in LLM-based agents have led to significant progress in automatic software engineering, particularly in software maintenance and evolution. Despite these encouraging advances, current research faces two major challenges. First, SOTA performance primarily depends on closed-source models, which significantly limits the technology's accessibility, and potential for customization in diverse SE tasks. Second, these models are predominantly trained on static code data, lacking a deep understanding of the dynamic interactions, iterative problem-solving processes, and evolutionary characteristics inherent in software development. To address these challenges, our study adopts a software engineering perspective. We recognize that real-world software maintenance and evolution processes encompass not only static code data but also developers' thought processes, utilization of external tools, and the interaction between different functional personnel. Consequently, we introduce the Lingma SWE-GPT series, comprising Lingma SWE-GPT 7B and 72B. By learning from and simulating real-world code submission activities, Lingma SWE-GPT systematically incorporates the dynamic interactions and iterative problem-solving inherent in software development process, thereby achieving a more comprehensive understanding of software improvement processes. We conducted experimental evaluations using SWE-bench Verified benchmark. The results demonstrate that Lingma SWE-GPT 72B successfully resolves 30.20% of the GitHub issues, marking a significant improvement in automatic issue resolution (22.76% relative improvement compared to Llama 3.1 405B), approaching the performance of closed-source models (31.80\% issues of GPT-4o resolved). Notably, Lingma SWE-GPT 7B resolves 18.20% of the issues, highlighting the potential for applying smaller models to ASE tasks.

For agents

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

get_harvested_code_for_paper("2411.00622")
get_code_for_paper("2411.00622")
have("2411.00622")

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

curl https://syntology.ai/api/ran/2411.00622.json

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

[![Syntology run record](https://syntology.ai/api/ran/2411.00622.svg)](https://syntology.ai/paper/2411.00622)

Connect an agent — have() is free.