pith. sign in

arxiv: 2410.17238 · v1 · pith:GOTGYCX7new · submitted 2024-10-22 · 💻 cs.AI · cs.CL· cs.LG· cs.SE

SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning

classification 💻 cs.AI cs.CLcs.LGcs.SE
keywords learningmachineagentsautomlselaagent-basedacrossautomated
0
0 comments X
read the original abstract

Automated Machine Learning (AutoML) approaches encompass traditional methods that optimize fixed pipelines for model selection and ensembling, as well as newer LLM-based frameworks that autonomously build pipelines. While LLM-based agents have shown promise in automating machine learning tasks, they often generate low-diversity and suboptimal code, even after multiple iterations. To overcome these limitations, we introduce Tree-Search Enhanced LLM Agents (SELA), an innovative agent-based system that leverages Monte Carlo Tree Search (MCTS) to optimize the AutoML process. By representing pipeline configurations as trees, our framework enables agents to conduct experiments intelligently and iteratively refine their strategies, facilitating a more effective exploration of the machine learning solution space. This novel approach allows SELA to discover optimal pathways based on experimental feedback, improving the overall quality of the solutions. In an extensive evaluation across 20 machine learning datasets, we compare the performance of traditional and agent-based AutoML methods, demonstrating that SELA achieves a win rate of 65% to 80% against each baseline across all datasets. These results underscore the significant potential of agent-based strategies in AutoML, offering a fresh perspective on tackling complex machine learning challenges.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

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

  1. ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments

    cs.LG 2026-06 unverdicted novelty 7.0

    ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.

  2. KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems

    cs.AI 2025-08 unverdicted novelty 7.0

    KompeteAI accelerates AutoML pipeline evaluation 6.9 times and beats prior systems by 3% on MLE-Bench through candidate merging, external RAG, and predictive early scoring.

  3. Learning the ARTS of Search for Automated Discovery

    cs.AI 2026-06 unverdicted novelty 6.0

    ARTS improves automated scientific discovery by using reasoning LMs with test-time training to separate hypothesis merit from execution quality in tree search, achieving 15.3% relative gains on 22 MLGym and MLEBench tasks.

  4. Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization

    cs.MA 2026-06 unverdicted novelty 6.0

    An LLM-orchestrated multi-agent framework for end-to-end BDaaS automation with drift awareness is proposed and evaluated on tabular benchmarks for improved lifecycle reliability over baselines.

  5. DataMaster: Data-Centric Autonomous AI Research

    cs.LG 2026-05 unverdicted novelty 6.0

    DataMaster deploys an AI agent to autonomously engineer data via tree search over external sources, shared candidate pools, and memory of past outcomes, yielding 32% higher medal rates on MLE-Bench Lite and a small GP...

  6. DataMaster: Data-Centric Autonomous AI Research

    cs.LG 2026-05 unverdicted novelty 6.0

    DataMaster autonomously optimizes data via tree search and shared memory, raising medal rate 32.27% on MLE-Bench Lite and beating the base instruct model on GPQA.

  7. AgentGA: Evolving Code Solutions in Agent-Seed Space

    cs.AI 2026-04 unverdicted novelty 6.0

    AgentGA uses a genetic algorithm to evolve agent seeds and achieves 74.52% human-exceeding performance on tabular AutoML tasks versus 54.15% for the AIDE baseline.

  8. AgentGA: Evolving Code Solutions in Agent-Seed Space

    cs.AI 2026-04 unverdicted novelty 6.0

    AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.

  9. LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning

    cs.LG 2026-01 unverdicted novelty 6.0

    LLM agents iteratively generate and optimize data processing strategies for fine-tuning, delivering over 80% win rates versus unprocessed data and 65% versus LLM-based AutoML baselines while cutting search time by up to 10x.