REVIEW 15 cited by
AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data pipelines through a collaborative multi-agent system. AutoKaggle implements an iterative development process that combines code execution, debugging, and comprehensive unit testing to ensure code correctness and logic consistency. The framework offers highly customizable workflows, allowing users to intervene at each phase, thus integrating automated intelligence with human expertise. Our universal data science toolkit, comprising validated functions for data cleaning, feature engineering, and modeling, forms the foundation of this solution, enhancing productivity by streamlining common tasks. We selected 8 Kaggle competitions to simulate data processing workflows in real-world application scenarios. Evaluation results demonstrate that AutoKaggle achieves a validation submission rate of 0.85 and a comprehensive score of 0.82 in typical data science pipelines, fully proving its effectiveness and practicality in handling complex data science tasks.
Forward citations
Cited by 15 Pith papers
-
SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner
SWE-Flow synthesizes incremental, test-driven development tasks from real GitHub projects and shows that fine-tuning Qwen2.5-Coder-32B-Instruct on them improves performance on the resulting SWE-Flow-Bench benchmark.
-
DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?
DSAgentBench is a new 275-task benchmark for end-to-end data science in real computer environments, where current AI agents, especially open-source ones, mostly fail.
-
Reinforcement Learning for Machine Learning Engineering Agents
RL-trained Qwen2.5-3B outperforms prompted Claude-3.5-Sonnet and GPT-4o on 12 MLEBench tasks by an average of 22% and 24%, using two targeted RL modifications.
-
IFEvalCode: Controlled Code Generation
A 1,620-sample, 8-language, Chinese/English benchmark separates code correctness from instruction-following and shows instruction compliance is far lower than correctness across 40+ LLMs.
-
Coding Triangle: How Does Large Language Model Understand Code?
The Coding Triangle framework evaluates LLMs on editorials, code, and test cases, revealing that models are self-consistent yet lack diversity and that model mixtures improve robustness.
-
ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
ML-Master, a new AI4AI agent, achieves 29.3% medals on MLE-Bench by integrating MCTS-style exploration with reasoning steered by a compact adaptive memory, surpassing prior agents in half the time.
-
BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research
BioDSA-1K is a large, publication-grounded benchmark for evaluating AI agents on biomedical hypothesis validation, including non-verifiable cases.
-
Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard
An LLM prompted with nearest-neighbor labels and external model predictions performs instance-level ensembling for tabular data, reaching the best average rank on TinyBench2.
-
Evaluating and Aligning CodeLLMs on Human Preference
A new 397-sample, 44-language code Q&A benchmark with LLM-judged human preference reveals gaps between open and proprietary code models and a 20B-token synthetic instruction corpus.
-
DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
DrugAgent, a Planner-Instructor multi-agent LLM framework with drug-discovery documentation, beats ReAct by 4.92% ROC-AUC on DTI and exceeds general agents on two of three tasks in its Top3 variant.
-
Continuous Improvement and Parallel Autonomous Exploration: An LLM-Agent Framework for Searching Large Solution Spaces
A leaderboard-driven LLM-agent framework improved product-to-catalog matching coverage from a 33.3% baseline to 47.8-57.4% with one agent and up to 69.4% with five parallel agents, while parallel agents explored quali...
-
Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering
Matryoshka Agent’s orchestrator–sub-agent hierarchy plus tree-ranked RL raises MLE-Dojo HumanRank, letting a 4B orchestrator approach o4-mini and giving a 30B coder up to 36.7% relative gain.
-
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
MLZero, an LLM-based multi-agent system with perception and dual memory, reports 92 percent success on a new 25-task multimodal AutoML benchmark and the best average rank on MLE-Bench Lite.
-
MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
An open Gym-style environment running 200+ Kaggle competitions lets LLM agents iterate on ML solutions and provides a benchmark for training and evaluating them.
-
Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey
A survey that organizes LLM-based complex problem solving into three components, multi-step reasoning, domain knowledge, and result verification, and reviews methods and challenges across four application domains.
Discussion (0). Continue with ORCID to comment.