Pith. sign in

REVIEW 16 cited by

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2410.02958 v2 pith:KZEKHK4A submitted 2024-10-03 cs.LG cs.AIcs.CLcs.MA

Patara Trirat , Wonyong Jeong , Sung Ju Hwang This is my paper · ORCID
classification cs.LGcs.AIcs.CLcs.MA
keywords automlautoml-agentdevelopmentprocesssearchautomatingbuilddata
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up complex tools, which is in general time-consuming and requires a large amount of human effort. Therefore, recent works have started exploiting large language models (LLM) to lessen such burden and increase the usability of AutoML frameworks via a natural language interface, allowing non-expert users to build their data-driven solutions. These methods, however, are usually designed only for a particular process in the AI development pipeline and do not efficiently use the inherent capacity of the LLMs. This paper proposes AutoML-Agent, a novel multi-agent framework tailored for full-pipeline AutoML, i.e., from data retrieval to model deployment. AutoML-Agent takes user's task descriptions, facilitates collaboration between specialized LLM agents, and delivers deployment-ready models. Unlike existing work, instead of devising a single plan, we introduce a retrieval-augmented planning strategy to enhance exploration to search for more optimal plans. We also decompose each plan into sub-tasks (e.g., data preprocessing and neural network design) each of which is solved by a specialized agent we build via prompting executing in parallel, making the search process more efficient. Moreover, we propose a multi-stage verification to verify executed results and guide the code generation LLM in implementing successful solutions. Extensive experiments on seven downstream tasks using fourteen datasets show that AutoML-Agent achieves a higher success rate in automating the full AutoML process, yielding systems with good performance throughout the diverse domains.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Scaling Multi-agent Systems: A Smart Middleware for Improving Agent Interactions

    cs.MA 2026-04 unverdicted novelty 6.0 of 10

    Cognitive Fabric Nodes middleware improves multi-agent LLM system performance by over 10% on HotPotQA and MuSiQue datasets by elevating memory to an active substrate for topology selection, semantic grounding, securit...

  2. iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML

    cs.LG 2026-02 conditional novelty 6.0 of 10

    iML's contract-based modular code generation with runtime verification reports 85% valid submissions and a 45% medal rate on MLE-BENCH, ahead of MLZero, MLE-STAR, and AutoML-Agent.

  3. EXP-Bench: Can AI Conduct AI Research Experiments?

    cs.AI 2025-05 conditional novelty 6.0 of 10

    EXP-Bench is a new benchmark of 461 end-to-end AI research experiments, and leading AI agents complete fewer than 1 percent of them successfully.

  4. Can AI Agents Design and Implement Drug Discovery Pipelines?

    cs.AI 2025-04 conditional novelty 6.0 of 10

    The DO Challenge benchmark and Deep Thought multi-agent system show frontier LLM agents can roughly match non-expert humans on a synthetic virtual screening task, while remaining far behind expert-designed solutions.

  5. TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning

    cs.AI 2025-02 reject novelty 6.0 of 10

    A teacher LLM guides an attention-based DRL student for autonomous driving, reporting improved success rates in simulation, though with several unstated implementation details.

  6. Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models

    cs.IR 2026-01 reject novelty 5.0 of 10

    A two-framework testbed comparison claims mem0 is Pareto-optimal over Graphiti for distributed LLM agents because its lower cost is paired with accuracy that is not significantly different.

  7. Aleks: AI powered Multi Agent System for Autonomous Scientific Discovery via Data-Driven Approaches in Plant Science

    cs.AI 2025-08 conditional novelty 5.0 of 10

    A three-agent LLM system, Aleks, autonomously chooses problem framing, features, and models for plant disease prediction, with domain knowledge and shared memory improving coherence across iterations.

  8. Interpretable by Design: MH-AutoML for Transparent and Efficient Android Malware Detection without Compromising Performance

    cs.CR 2025-06 conditional novelty 5.0 of 10

    MH-AutoML is a domain-specific AutoML framework for Android malware detection that combines automated modeling with built-in interpretability, and its evaluation shows competitive recall and higher transparency scores...

  9. CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    CoNav lets a frozen 3D-text model pass spatial text hints to a lightly fine-tuned image-text navigation agent, improving path efficiency on several VLN benchmarks, though not all claimed state-of-the-art results hold.

  10. Large Language Model-Empowered Interactive Load Forecasting

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A multi-agent LLM framework enables interactive, natural-language steering of load forecasting pipelines and reports improved accuracy when users provide informed guidance.

  11. MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

    cs.MA 2025-05 conditional novelty 5.0 of 10

    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.

  12. MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

    cs.LG 2025-05 conditional novelty 5.0 of 10

    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.

  13. Optimization Problem Solving Can Transition to Evolutionary Agentic Workflows

    math.OC 2025-05 conditional novelty 5.0 of 10

    An evolutionary loop of foundation-model agents could automate the full optimization pipeline, but the paper's evidence only covers two isolated components.

  14. ADL: A Declarative Language for Agent-Based Chatbots

    cs.MA 2025-04 conditional novelty 5.0 of 10

    ADL defines four agent types (knowledge base, LLM, flow, ensemble) with natural-language conditions, all implemented in an open-source interpreter named MICA.

  15. Evaluation of Large Language Model-Driven AutoML in Data and Model Management from Human-Centered Perspective

    cs.HC 2025-07 reject novelty 4.0 of 10

    A 15-participant within-subjects study claims LLM-driven AutoML outperforms traditional AutoML on speed, accuracy, and usability, though supporting data are not provided and several numbers conflict.

  16. LLM-based Multi-Agent Systems: Techniques and Business Perspectives

    cs.AI 2024-11 unverdicted novelty 3.0 of 10

    LLM-based multi-agent systems, with standardized protocols and monetization incentives, are forecast to become the next AI business paradigm.

Pith tools