{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mlcopilot-unleashing-the-power-of-large","title":"MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks","arxiv_id":"2304.14979","date":"2023-04-28","proceeding":null,"authors":["Lei Zhang","Yuge Zhang","Kan Ren","Dongsheng Li","Yuqing Yang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2304.14979v2","url_pdf":"https://arxiv.org/pdf/2304.14979v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mlcopilot-unleashing-the-power-of-large","repo_url":"https://github.com/microsoft/CoML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"code-generation","task_name":"Code Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-dseval-leetcode","task":"Code Generation","dataset":"DSEval-LeetCode","model":"CoML","rank_in_archive_order":4,"of":5,"metrics":{"Pass Rate":"42.5","w/o Intact":"42.5","w/o PE":"62.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.14979","atlas_url":"https://app.syntology.ai/?focus=2304.14979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.14979"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/CoML","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":13},"by_repo_kind":{"official":{"samples":13,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3c4703bbbd99a477","entry":"add_indent","repo":"microsoft/CoML","repo_kind":"official","path":"coml/prompt_utils.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/prompt_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c4703bbbd99a477"}},{"code_sha256_prefix":"dae91c4c79f12360","entry":"canonicalize_config","repo":"microsoft/CoML","repo_kind":"official","path":"coml/configagent/experience.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/configagent/experience.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dae91c4c79f12360"}},{"code_sha256_prefix":"e4fe9e1b291b5d57","entry":"canonicalize_task","repo":"microsoft/CoML","repo_kind":"official","path":"coml/configagent/experience.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/configagent/experience.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4fe9e1b291b5d57"}},{"code_sha256_prefix":"6ac8cd0ceb467ce7","entry":"describe_variable","repo":"microsoft/CoML","repo_kind":"official","path":"coml/prompt_utils.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/prompt_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ac8cd0ceb467ce7"}},{"code_sha256_prefix":"5f24dfec2db46a2b","entry":"evaluate_configs","repo":"microsoft/CoML","repo_kind":"official","path":"coml/configagent/surrogate_utils.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/configagent/surrogate_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f24dfec2db46a2b"}},{"code_sha256_prefix":"8a9ff381ef3920b0","entry":"format_prompt","repo":"microsoft/CoML","repo_kind":"official","path":"coml/configagent/suggest.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/configagent/suggest.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a9ff381ef3920b0"}},{"code_sha256_prefix":"b42b7295bb687786","entry":"gen_space_description","repo":"microsoft/CoML","repo_kind":"official","path":"coml/configagent/space.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/configagent/space.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b42b7295bb687786"}},{"code_sha256_prefix":"1c275ce23e9573c9","entry":"lida_dataframe_describe","repo":"microsoft/CoML","repo_kind":"official","path":"coml/prompt_utils.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/prompt_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c275ce23e9573c9"}},{"code_sha256_prefix":"03dc5a4b614de51e","entry":"parse_cell_outputs","repo":"microsoft/CoML","repo_kind":"official","path":"coml/ipython_utils.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/ipython_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03dc5a4b614de51e"}},{"code_sha256_prefix":"e913cc4ff0eaf7fb","entry":"parse_code","repo":"microsoft/CoML","repo_kind":"official","path":"coml/core.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e913cc4ff0eaf7fb"}},{"code_sha256_prefix":"c9133b26f459c40b","entry":"parse_fix","repo":"microsoft/CoML","repo_kind":"official","path":"coml/core.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/core.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9133b26f459c40b"}},{"code_sha256_prefix":"2b8e081afe161e7e","entry":"process_history_df","repo":"microsoft/CoML","repo_kind":"official","path":"coml/configagent/surrogate_utils.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/configagent/surrogate_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b8e081afe161e7e"}},{"code_sha256_prefix":"56b78125af195f36","entry":"train_surrogate","repo":"microsoft/CoML","repo_kind":"official","path":"coml/configagent/surrogate_utils.py","file_url":"https://github.com/microsoft/CoML/blob/HEAD/coml/configagent/surrogate_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56b78125af195f36"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}