Papers › MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks

MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks

28 Apr 2023arXiv:2304.14979archive 2025-07-28

Lei Zhang, Yuge Zhang, Kan Ren, Dongsheng Li, Yuqing Yang

The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The predominant approaches towards the automation of solving ML tasks (e.g., AutoML) are often time-consuming and hard to understand for human developers. In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches. In this paper, we aim to bridge the gap between machine intelligence and human knowledge by introducing a novel framework, which leverages the state-of-the-art large language models to develop ML solutions for novel tasks. We showcase the possibility of extending the capability of LLMs to comprehend structured inputs and perform thorough reasoning for solving novel ML tasks. And we find that, after some dedicated design, the LLM can (i) observe from the existing experiences of ML tasks and (ii) reason effectively to deliver promising results for new tasks. The solution generated can be used directly to achieve high levels of competitiveness. Examples and code available at https://github.com/microsoft/CoML.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2304.14979")

Code

Syntology Ran 0 of 13 code samples harvested from 1 repository linked to this paper; 13 have no recorded run.

By repository: official repository: 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

microsoft/CoML officialmentioned in papermentioned on GitHubMIT 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

13 samples harvested; 0 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

13unverified

Licence: 0 of the 13 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 microsoft/CoML. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

add_indent microsoft/CoML/coml/prompt_utils.py official repository unverified MIT (permissive) · 3c4703bbbd99a477 · report
canonicalize_config microsoft/CoML/coml/configagent/experience.py official repository unverified MIT (permissive) · dae91c4c79f12360 · report
canonicalize_task microsoft/CoML/coml/configagent/experience.py official repository unverified MIT (permissive) · e4fe9e1b291b5d57 · report
describe_variable microsoft/CoML/coml/prompt_utils.py official repository unverified MIT (permissive) · 6ac8cd0ceb467ce7 · report
evaluate_configs microsoft/CoML/coml/configagent/surrogate_utils.py official repository unverified MIT (permissive) · 5f24dfec2db46a2b · report
format_prompt microsoft/CoML/coml/configagent/suggest.py official repository unverified MIT (permissive) · 8a9ff381ef3920b0 · report
gen_space_description microsoft/CoML/coml/configagent/space.py official repository unverified MIT (permissive) · b42b7295bb687786 · report
lida_dataframe_describe microsoft/CoML/coml/prompt_utils.py official repository unverified MIT (permissive) · 1c275ce23e9573c9 · report
parse_cell_outputs microsoft/CoML/coml/ipython_utils.py official repository unverified MIT (permissive) · 03dc5a4b614de51e · report
parse_code microsoft/CoML/coml/core.py official repository unverified MIT (permissive) · e913cc4ff0eaf7fb · report
parse_fix microsoft/CoML/coml/core.py official repository unverified MIT (permissive) · c9133b26f459c40b · report
process_history_df microsoft/CoML/coml/configagent/surrogate_utils.py official repository unverified MIT (permissive) · 2b8e081afe161e7e · report
train_surrogate microsoft/CoML/coml/configagent/surrogate_utils.py official repository unverified MIT (permissive) · 56b78125af195f36 · report

Tasks

AutoMLCode Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation DSEval-LeetCode CoML Pass Rate 42.5 #4 of 5 Archive leaderboard report
Code Generation DSEval-LeetCode CoML w/o Intact 42.5 #4 of 5 Archive leaderboard report
Code Generation DSEval-LeetCode CoML w/o PE 62.5 #4 of 5 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