Papers › Self-collaboration Code Generation via ChatGPT

Self-collaboration Code Generation via ChatGPT

15 Apr 2023arXiv:2304.07590links table onlyarchive 2025-07-28

Yihong Dong, Xue Jiang, Zhi Jin, Ge Li

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

Although Large Language Models (LLMs) have demonstrated remarkable code-generation ability, they still struggle with complex tasks. In real-world software development, humans usually tackle complex tasks through collaborative teamwork, a strategy that significantly controls development complexity and enhances software quality. Inspired by this, we present a self-collaboration framework for code generation employing LLMs, exemplified by ChatGPT. Specifically, through role instructions, 1) Multiple LLM agents act as distinct `experts', each responsible for a specific subtask within a complex task; 2) Specify the way to collaborate and interact, so that different roles form a virtual team to facilitate each other's work, ultimately the virtual team addresses code generation tasks collaboratively without the need for human intervention. To effectively organize and manage this virtual team, we incorporate software-development methodology into the framework. Thus, we assemble an elementary team consisting of three LLM roles (i.e., analyst, coder, and tester) responsible for software development's analysis, coding, and testing stages. We conduct comprehensive experiments on various code-generation benchmarks. Experimental results indicate that self-collaboration code generation relatively improves 29.9%-47.1% Pass@1 compared to the base LLM agent. Moreover, we showcase that self-collaboration could potentially enable LLMs to efficiently handle complex repository-level tasks that are not readily solved by the single LLM agent.

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

Syntology 17 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 17 samples from 1 repository, 11 ran (11 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 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

YihongDong/Self-collaboration-Code-Generation officialmentioned on GitHubMITSyntology: 17 samples, 11 ran (0 instrument-failed) · 6 unverified report
besser-pearl/agentic-bpmn mentioned on GitHubMITSyntology: not harvested 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

17 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 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.

11ran
6unverified

Licence: 0 of the 17 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 YihongDong/Self-collaboration-Code-Generation. “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.

YihongDong/Self-collaboration-Code-Generation official repository 17 samples, 11 ran (0 instrument-failed) · 6 unverified
code_truncate core/utils.py ran fingerprinted MIT (permissive) · 39ca69f20203b0e1 · report fixture: signature response:str/0/str · returned str · level recorded 2026-09-25
code_truncate_regex core/utils.py ran fingerprinted MIT (permissive) · 4d6900765a680c9f · report fixture: signature code:str/0/str · returned str · level recorded 2026-09-25
extract_patch core/patch_utils.py ran fingerprinted MIT (permissive) · 40263bfc7c17c517 · report fixture: signature response:str/0/str · returned str · level recorded 2026-09-25
get_image_name in 5 papers run_swe_docker.py ran fingerprinted MIT (permissive) · 8d702cbfc56a7d48 · report fixture: signature instance_id:str/0/str · returned str · level recorded 2026-09-25
get_repo_structure core/repo_tools.py ran fingerprinted MIT (permissive) · 34c188c42a3e46a9 · report fixture: signature repo_path:str/0/str, max_depth:int/0/int · returned str · level recorded 2026-09-25
openai_config core/config.py ran MIT (permissive) · ba1bea1b924882e1 · report fixture: signature model:str/0/str, max_tokens:int/0/int, temperature:float/0/float, top_p:float/0/float · returned ModelConfig · level recorded 2026-09-25
prompt_split_humaneval core/utils.py ran MIT (permissive) · 91120a9f594cb6e3 · report fixture: signature prompt:str/0/str, mehotd_name:str/0/str · returned tuple · level recorded 2026-09-26
read_file in 112 papers core/repo_tools.py ran fingerprinted MIT (permissive) · bac44134ee8d1581 · report fixture: signature repo_path:str/0/str, file_path:str/0/str · returned str · level recorded 2026-09-25
repair_patch core/patch_utils.py ran fingerprinted MIT (permissive) · 5b0f4aae224d17d9 · report fixture: signature patch:str/0/str · returned str · level recorded 2026-09-25
strip_context_lines core/patch_utils.py ran fingerprinted MIT (permissive) · 4699f7376865432a · report fixture: signature patch:str/0/str · returned str · level recorded 2026-09-25
unsafe_execute core/sandbox.py ran fingerprinted MIT (permissive) · 584acc1f9637179b · report fixture: signature code:str/0/str, report:str/0/str · returned str · level recorded 2026-09-25
call_chatgpt in 5 papers core/backend.py unverified MIT (permissive) · edb3468adda5e752 · report
call_llm in 14 papers core/backend.py unverified MIT (permissive) · 6b210bdeeae33ffc · report
call_llm_with_tools core/backend.py unverified MIT (permissive) · 93b3e7a2b08c74b7 · report
clone_repo core/repo_tools.py unverified MIT (permissive) · 85dcee64dcb03ae5 · report
image_exists run_swe_docker.py unverified MIT (permissive) · 6d314c06f83ec007 · report
start_container run_swe_docker.py unverified MIT (permissive) · c94bc015446c731b · report

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