TAGAL uses an agentic LLM loop, generation plus feedback, to produce synthetic tabular data without LLM training, matching trained models on some datasets and beating the training-free EPIC baseline.
Journal of artificial intelligence research16, 321–357 (2002)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TAGAL: Tabular Data Generation using Agentic LLM Methods
TAGAL uses an agentic LLM loop, generation plus feedback, to produce synthetic tabular data without LLM training, matching trained models on some datasets and beating the training-free EPIC baseline.