{"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/mlr-copilot-autonomous-machine-learning","title":"MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents","arxiv_id":"2408.14033","date":"2024-08-26","proceeding":null,"authors":["Ruochen Li","Teerth Patel","Qingyun Wang","Xinya Du"],"abstract":"Machine learning research, crucial for technological advancements and innovation, often faces significant challenges due to its inherent complexity, slow pace of experimentation, and the necessity for specialized expertise. Motivated by this, we present a new systematic framework, autonomous Machine Learning Research with large language models (MLR-Copilot), designed to enhance machine learning research productivity through the automatic generation and implementation of research ideas using Large Language Model (LLM) agents. The framework consists of three phases: research idea generation, experiment implementation, and implementation execution. First, existing research papers are used to generate hypotheses and experimental plans vis IdeaAgent powered by LLMs. Next, the implementation generation phase translates these plans into executables with ExperimentAgent. This phase leverages retrieved prototype code and optionally retrieves candidate models and data. Finally, the execution phase, also managed by ExperimentAgent, involves running experiments with mechanisms for human feedback and iterative debugging to enhance the likelihood of achieving executable research outcomes. We evaluate our framework on five machine learning research tasks and the experimental results show the framework's potential to facilitate the research progress and innovations.","url_abs":"https://arxiv.org/abs/2408.14033v2","url_pdf":"https://arxiv.org/pdf/2408.14033v2.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":"mlr-copilot-autonomous-machine-learning","repo_url":"https://github.com/du-nlp-lab/mlr-copilot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.14033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14033"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/du-nlp-lab/mlr-copilot","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":7},"by_repo_kind":{"official":{"samples":10,"ran":3,"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":10,"samples":[{"code_sha256_prefix":"8fbba13275be664e","entry":"check_file_read_only","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/low_level_actions.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/low_level_actions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8fbba13275be664e"}},{"code_sha256_prefix":"53250bc9bc9a4820","entry":"mkl_error","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/plot.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/plot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53250bc9bc9a4820"}},{"code_sha256_prefix":"357dc7ee438a7576","entry":"oom_error","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/plot.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/plot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"357dc7ee438a7576"}},{"code_sha256_prefix":"1e14d9132d242b44","entry":"complete_text_openai","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/llm.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/llm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e14d9132d242b44"}},{"code_sha256_prefix":"f18ec77be53a6de1","entry":"edit_script","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/high_level_actions.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/high_level_actions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f18ec77be53a6de1"}},{"code_sha256_prefix":"9c55f0596ab5430b","entry":"estimate_tokens","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/plot.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/plot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9c55f0596ab5430b"}},{"code_sha256_prefix":"2868580e4a832fe7","entry":"get_task_info","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/prepare_task.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/prepare_task.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2868580e4a832fe7"}},{"code_sha256_prefix":"d6d0c6d7bde0bdcc","entry":"normalize_args_kwargs","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/low_level_actions.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/low_level_actions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d6d0c6d7bde0bdcc"}},{"code_sha256_prefix":"fb1b6759b6496469","entry":"reflection","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/high_level_actions.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/high_level_actions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb1b6759b6496469"}},{"code_sha256_prefix":"82316345fa4a591f","entry":"understand_file","repo":"du-nlp-lab/mlr-copilot","repo_kind":"official","path":"reactagent/high_level_actions.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/high_level_actions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82316345fa4a591f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}