LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)
cs.AI
Submitted: 2026-06-08
Updated: 2026-10-12
Project page: https://goodenhak.github.io/LATTEArena
Terminology
Sources
- LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
- GPT-4 Technical Report
- Knowledge-Informed Automatic Feature Extraction via Collaborative Large Language Model Agents
- AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
- Retrieval-Augmented Generation for Large Language Models: A Survey
- EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
- AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
- A Survey of Context Engineering for Large Language Models
- Automated Machine Learning: From Principles to Practices
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Hyper-Parameter Optimization: A Review of Algorithms and Applications
- Retrieval-Augmented Feature Generation for Domain-Specific Classification
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems