Papers › SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

9 Jan 2025arXiv:2501.05040archive 2025-07-28

Chengxing Xie, Bowen Li, Chang Gao, He Du, Wai Lam, Difan Zou, Kai Chen

Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks. One significant application of LLMs is in tackling software engineering challenges, particularly in resolving real-world tasks on GitHub by fixing code based on the issues reported by the users. However, many current approaches rely on proprietary LLMs, which limits reproducibility, accessibility, and transparency. The critical components of LLMs for addressing software engineering issues and how their capabilities can be effectively enhanced remain unclear. To address these challenges, we introduce SWE-Fixer, a novel open-source framework designed to effectively and efficiently resolve GitHub issues. SWE-Fixer comprises two essential modules: a code file retrieval module and a code editing module. The retrieval module employs BM25 along with a lightweight model to achieve coarse-to-fine file retrieval. Subsequently, the code editing module utilizes the other model to generate patches for the identified files. To mitigate the lack of publicly available datasets, we compile an extensive dataset that includes 110K GitHub issues along with their corresponding patches and train the two models of SWE-Fixer separately. We assess our approach on the SWE-Bench Lite and Verified benchmarks, achieving competitive performance among open-source models with scores of 22.0% and 30.2%. Furthermore, SWE-Fixer reaches state-of-the-art performance (24.7% on Lite and 32.8% on Verified) with PASS_TO_PASS (P2P) filtering. Additionally, our approach requires only two model calls per instance, making it significantly more efficient than existing methods. These results highlight the effectiveness of SWE-Fixer in real-world code-fixing scenarios. We will make our model, dataset, and code publicly available at https://github.com/InternLM/SWE-Fixer.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (internlm/swe-fixer) was not harvested; the 15 samples below come from 1 community repository.

Syntology 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 15 samples from 1 repository, 13 ran (13 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

internlm/swe-fixer officialmentioned in papermentioned on GitHubSyntology: not harvested report
jorge-martinez-gil/graphcodebert-feature-integration mentioned on GitHubpytorchMITSyntology: 15 samples, 13 ran (0 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

13ran
2unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from jorge-martinez-gil/graphcodebert-feature-integration. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

jorge-martinez-gil/graphcodebert-feature-integration community (archive-listed) 15 samples, 13 ran (0 instrument-failed) · 2 unverified
bootstrap_metric_ci src/featfuse/stats.py ran MIT (permissive) · 5556819fa8611c78 · report fixture: signature metric_fn:callable/0/?, y_true:ndarray/1/int, y_pred_or_score:ndarray/1/int, n_boot:int/0/int, confidence:float/0/float, seed:int/0/int · returned dict · level recorded 2026-09-24
compute_metrics in 208 papers legacy/fine-tunning-graphcodebert-karnalim-with-features.py ran MIT (permissive) · c17d5d78451bbd57 · report fixture: signature p:tuple/1/ndarray · returned dict · level recorded 2026-09-25
config_hash src/featfuse/reproducibility.py ran MIT (permissive) · 937c3bfd40cb3ca5 · report fixture: signature config:dict/0/? · returned str · level recorded 2026-09-24
expected_calibration_error in 12 papers src/featfuse/metrics.py ran MIT (permissive) · 4dc062f89cd64e1d · report fixture: signature y_true:ndarray/1/int, y_prob:ndarray/1/float, n_bins:int/0/int · returned float · level recorded 2026-09-25
get_classifier in 16 papers src/featfuse/experiment.py ran MIT (permissive) · 306fd49af7f42a7e · report fixture: signature name:str/0/str, seed:int/0/int · returned LogisticRegression · level recorded 2026-09-25
make_manifest src/featfuse/reproducibility.py ran MIT (permissive) · 2119a197049c004a · report fixture: signature config:dict/0/?, seed:int/0/int, extra:dict/0/? · returned dict · level recorded 2026-09-24
mcnemar_test src/featfuse/stats.py ran MIT (permissive) · 6189dbb4e2522b64 · report fixture: signature y_true:ndarray/1/int, pred_a:ndarray/1/int, pred_b:ndarray/1/int · returned dict · level recorded 2026-09-24
paired_bootstrap_diff src/featfuse/stats.py ran MIT (permissive) · 6fd9fc26f9ea8174 · report fixture: signature metric_fn:callable/0/?, y_true:ndarray/1/int, pred_a:ndarray/1/int, pred_b:ndarray/1/int, n_boot:int/0/int, confidence:float/0/float, seed:int/0/int · returned dict · level recorded 2026-09-25
plot_calibration src/featfuse/viz.py ran MIT (permissive) · 293e3be63397cd3b · report fixture: signature y_true:ndarray/1/int, y_prob:ndarray/1/float, path:str/0/str, n_bins:int/0/int, title:str/0/str · returned str · level recorded 2026-09-24
plot_feature_importance src/featfuse/viz.py ran MIT (permissive) · 111459a93cf871ff · report fixture: signature names:list/1/str, importances:list/1/float, path:str/0/str, title:str/0/str · returned str · level recorded 2026-09-24
plot_metric_bars src/featfuse/viz.py ran MIT (permissive) · 02bdd0d30c99b07a · report fixture: signature method_metrics:dict/0/?, metrics:list/1/str, path:str/0/str, title:str/0/str · returned str · level recorded 2026-09-24
set_seed in 49 papers src/featfuse/reproducibility.py ran fingerprinted MIT (permissive) · 0dfa44f5bdd15b72 · report fixture: signature seed:int/0/int, deterministic:bool/0/bool · returned int · level recorded 2026-09-24
similarity in 17 papers legacy/utils/java_sim_exec_opt.py ran fingerprinted MIT (permissive) · 0785ae298e13dd83 · report fixture: signature java_code1:str/0/str, java_code2:str/0/str · returned int · level recorded 2026-09-24
classification_metrics in 9 papers src/featfuse/metrics.py unverified MIT (permissive) · 1b12db6bf011d6fa · report
execute_java_code legacy/utils/java_sim_exec_opt.py unverified MIT (permissive) · 69d614ed324ad1a6 · report

Tasks

GitHub issue resolutionRetrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections