Papers › MapCoder: Multi-Agent Code Generation for Competitive Problem Solving

MapCoder: Multi-Agent Code Generation for Competitive Problem Solving

18 May 2024arXiv:2405.11403archive 2025-07-28

Md. Ashraful Islam, Mohammed Eunus Ali, Md Rizwan Parvez

Code synthesis, which requires a deep understanding of complex natural language problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests, presents a significant challenge. While large language models (LLMs) demonstrate impressive proficiency in natural language processing, their performance in code generation tasks remains limited. In this paper, we introduce a new approach to code generation tasks leveraging multi-agent prompting that uniquely replicates the full cycle of program synthesis as observed in human developers. Our framework, MapCoder, consists of four LLM agents specifically designed to emulate the stages of this cycle: recalling relevant examples, planning, code generation, and debugging. After conducting thorough experiments, with multiple LLM ablations and analyses across eight challenging competitive problem-solving and program synthesis benchmarks, MapCoder showcases remarkable code generation capabilities, achieving new state-of-the-art results (pass@1) on HumanEval (93.9%), MBPP (83.1%), APPS (22.0%), CodeContests (28.5%), and xCodeEval (45.3%). Moreover, our method consistently delivers superior performance across various programming languages and varying problem difficulties. We open-source our framework at https://github.com/Md-Ashraful-Pramanik/MapCoder.

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 (md-ashraful-pramanik/mapcoder) was not harvested; the 10 samples below come from 1 community repository.

Syntology 10 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 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): 10 samples from 1 repository, 6 ran (6 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.

md-ashraful-pramanik/mapcoder officialmentioned in papermentioned on GitHubMITSyntology: not harvested report
Luoji-zju/Agents4PLC_release mentioned on GitHubApache-2.0Syntology: 10 samples, 6 ran (0 instrument-failed) · 4 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

10 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 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.

6ran
4unverified

Licence: 0 of the 10 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 Luoji-zju/Agents4PLC_release. “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.

Luoji-zju/Agents4PLC_release community (archive-listed) 10 samples, 6 ran (0 instrument-failed) · 4 unverified
create_log_directory LLM4PLC_reproduce/run_efficiency.py ran Apache-2.0 (permissive) · de3a0618a914e97e · report fixture: signature spec_path:str/0/str, base_dir:str/0/str · returned tuple · level recorded 2026-09-24
generate_nl_description src/plcverif.py ran Apache-2.0 (permissive) · 464c0c08fefdf90c · report fixture: signature pattern_id:str/0/str, pattern_params:dict/0/? · returned str · level recorded 2026-09-24
input_with_timeout LLM4PLC_reproduce/run_efficiency_v2.py ran fingerprinted Apache-2.0 (permissive) · b4ae4f09792713f2 · report fixture: signature prompt:str/0/str, timeout:int/0/int, default:str/0/str · returned str · level recorded 2026-09-25
list_to_json_string src/tools.py ran fingerprinted Apache-2.0 (permissive) · b20bd1bc19f9f7df · report fixture: signature property_list:list/1/dict · returned str · level recorded 2026-09-24
rusty_compiler src/compiler.py ran Apache-2.0 (permissive) · f8a97b7fd226ab76 · report fixture: signature file_dir:str/0/str · returned bool · level recorded 2026-09-24
safe_repr src/tools.py ran fingerprinted Apache-2.0 (permissive) · e00def812098236a · report fixture: signature data:str/0/str · returned str · level recorded 2026-09-25
input_with_timeout LLM4PLC_reproduce/run_efficiency.py unverified Apache-2.0 (permissive) · fe740cfb7327d8b2 · report
nuXmv_model_checker LLM4PLC_reproduce/run_efficiency.py unverified Apache-2.0 (permissive) · 848bf700245e1978 · report
nuXmv_model_checker LLM4PLC_reproduce/run_efficiency_v2.py unverified Apache-2.0 (permissive) · d76fc1eb310fdfa3 · report
plcverif_call src/plcverif.py unverified Apache-2.0 (permissive) · a632c1e691ea6a16 · report

Tasks

Code GenerationHumanEvalProgram Synthesis

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Competition Pass@1 0.00% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Competition Pass@1000 8.80% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Competition Pass@5 0.00% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Competition Pass@any 8.80% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Interview Pass@1 0.70% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Interview Pass@1000 9.27% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Interview Pass@5 1.03% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Interview Pass@any 9.27% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Introductory Pass@1 1.30% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Introductory Pass@1000 25.00% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Introductory Pass@5 3.60% #16 of 18 Archive leaderboard report
Code Generation APPS MapCoder APPS-150-cherrypicked (GPT-4) Introductory Pass@any 25.00% #16 of 18 Archive leaderboard report
Code Generation CodeContests MapCoder (GPT-4) Test Set pass@1 28.5 #3 of 8 Archive leaderboard report
Code Generation CodeContests MapCoder (GPT-4) Test Set pass@5 35.2 #3 of 8 Archive leaderboard report
Code Generation CodeContests MapCoder (GPT-4) Val Set pass@1 28.5 #3 of 8 Archive leaderboard report
Code Generation HumanEval Mistral 7B Pass@1 93.9 #6 of 8 Archive leaderboard report
Code Generation MBPP o1-mini + MapCoder (Hamming.ai) Accuracy 93.2 #3 of 99 Archive leaderboard report
Code Generation MBPP MapCoder (GPT-4o) Accuracy 89.7 #9 of 99 Archive leaderboard report
Code Generation MBPP MapCoder (GPT-4) Accuracy 83.1 #17 of 99 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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