We lifted 13 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| microsoft/CoML | canonical | 0 of 13 |
| Function | Status | Where it lives |
|---|---|---|
| add_indent | Not yet run | microsoft/CoML/coml/prompt_utils.py code served (permissive licence) · get_code("3c4703bbbd99a477") |
| canonicalize_config | Not yet run | microsoft/CoML/coml/configagent/experience.py code served (permissive licence) · get_code("dae91c4c79f12360") |
| canonicalize_task | Not yet run | microsoft/CoML/coml/configagent/experience.py code served (permissive licence) · get_code("e4fe9e1b291b5d57") |
| describe_variable | Not yet run | microsoft/CoML/coml/prompt_utils.py code served (permissive licence) · get_code("6ac8cd0ceb467ce7") |
| evaluate_configs | Not yet run | microsoft/CoML/coml/configagent/surrogate_utils.py code served (permissive licence) · get_code("5f24dfec2db46a2b") |
| format_prompt | Not yet run | microsoft/CoML/coml/configagent/suggest.py code served (permissive licence) · get_code("8a9ff381ef3920b0") |
| gen_space_description | Not yet run | microsoft/CoML/coml/configagent/space.py code served (permissive licence) · get_code("b42b7295bb687786") |
| lida_dataframe_describe | Not yet run | microsoft/CoML/coml/prompt_utils.py code served (permissive licence) · get_code("1c275ce23e9573c9") |
| parse_cell_outputs | Not yet run | microsoft/CoML/coml/ipython_utils.py code served (permissive licence) · get_code("03dc5a4b614de51e") |
| parse_code | Not yet run | microsoft/CoML/coml/core.py code served (permissive licence) · get_code("e913cc4ff0eaf7fb") |
| parse_fix | Not yet run | microsoft/CoML/coml/core.py code served (permissive licence) · get_code("c9133b26f459c40b") |
| process_history_df | Not yet run | microsoft/CoML/coml/configagent/surrogate_utils.py code served (permissive licence) · get_code("2b8e081afe161e7e") |
| train_surrogate | Not yet run | microsoft/CoML/coml/configagent/surrogate_utils.py code served (permissive licence) · get_code("56b78125af195f36") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.14979")
get_code_for_paper("2304.14979")
have("2304.14979")
Connect an agent — have() is free.