SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.17453 · ICML · 2024

DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning

Jun Wang, Ying Wen, Yi Chang, Cheng Deng, Siyuan Guo, Hechang Chen, Case 𝑐, ! 𝑙 !"# 𝑙 !"#

arXiv · PDF · Open in the Atlas

Code that ran

9 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.17453.json · badge: /api/ran/2402.17453.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
guosyjlu/DS-Agent canonical (classifier label)
classifier basis: census
9 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_metrics_for_classification Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guosyjlu/DS-Agent/deployment/experience_replay/chatgpt-prompt.py
pointer only (licence: NONE) · get_code("e48536a39e307f1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_metrics_for_classification Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guosyjlu/DS-Agent/deployment/experience_replay/enzyme-substrate.py
pointer only (licence: NONE) · get_code("c7c62555e1f51544")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

execute_script Ran
ran; our contract draft was wrong, not the code
guosyjlu/DS-Agent/deployment/execution.py
pointer only (licence: NONE) · get_code("34caab810cace413")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

predict Ran
ran, honoured the contract we drafted
guosyjlu/DS-Agent/deployment/experience_replay/airline-reviews.py
pointer only (licence: NONE) · get_code("6419d62b28f3cfc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

predict Ran
ran; our contract draft was wrong, not the code
guosyjlu/DS-Agent/deployment/experience_replay/chatgpt-prompt.py
pointer only (licence: NONE) · get_code("d168412c0d94b909")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

predict Ran
ran; our contract draft was wrong, not the code
guosyjlu/DS-Agent/deployment/experience_replay/enzyme-substrate.py
pointer only (licence: NONE) · get_code("a43e675ac4b0fed0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

train_model Ran
ran; our contract draft was wrong, not the code
guosyjlu/DS-Agent/deployment/experience_replay/airline-reviews.py
pointer only (licence: NONE) · get_code("0755b9a6ac3a5909")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

train_model Ran
ran; our contract draft was wrong, not the code
guosyjlu/DS-Agent/deployment/experience_replay/chatgpt-prompt.py
pointer only (licence: NONE) · get_code("53971733e3acbbb1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

train_model Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guosyjlu/DS-Agent/deployment/experience_replay/enzyme-substrate.py
pointer only (licence: NONE) · get_code("e759f3555c9dc70d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_metrics_for_regression Not yet run
unverified (harvested, no recorded run)
guosyjlu/DS-Agent/deployment/experience_replay/airline-reviews.py
pointer only (licence: NONE) · get_code("2b03d09920c8d2a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_case Not yet run
unverified (harvested, no recorded run)
guosyjlu/DS-Agent/deployment/prompt.py
pointer only (licence: NONE) · get_code("6d0f8f6dd1bc8b2f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_prompt Not yet run
unverified (harvested, no recorded run)
guosyjlu/DS-Agent/deployment/prompt.py
pointer only (licence: NONE) · get_code("15c1e503e527a5bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_task Not yet run
unverified (harvested, no recorded run)
guosyjlu/DS-Agent/deployment/prompt.py
pointer only (licence: NONE) · get_code("a45eb6f9978ac8b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, guosyjlu/DS-Agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we investigate the potential of large language models (LLMs) based agents to automate data science tasks, with the goal of comprehending task requirements, then building and training the best-fit machine learning models. Despite their widespread success, existing LLM agents are hindered by generating unreasonable experiment plans within this scenario. To this end, we present DS-Agent, a novel automatic framework that harnesses LLM agent and case-based reasoning (CBR). In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which can flexibly capitalize on the expert knowledge from Kaggle, and facilitate consistent performance improvement through the feedback mechanism. Moreover, DS-Agent implements a low-resource deployment stage with a simplified CBR paradigm to adapt past successful solutions from the development stage for direct code generation, significantly reducing the demand on foundational capabilities of LLMs. Empirically, DS-Agent with GPT-4 achieves 100% success rate in the development stage, while attaining 36% improvement on average one pass rate across alternative LLMs in the deployment stage. In both stages, DS-Agent achieves the best rank in performance, costing $1.60 and $0.13 per run with GPT-4, respectively. Our data and code are open-sourced at https: //github.com/guosyjlu/DS-Agent.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.17453")
get_code_for_paper("2402.17453")
have("2402.17453")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.17453.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.17453.svg)](https://syntology.ai/paper/2402.17453)

Connect an agent — have() is free.