mlsanityData to 7 Oct 2026

Curate-Train-Refine: A Closed-Loop Agentic Framework for Zero Shot Classification

arXiv 2601.16530 ↗First posted 23 Jan 2026cs.CL cs.LGcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large language models (LLMs) and high-capacity encoders have advanced zero and few-shot classification, but their inference cost and latency limit practical deployment. We propose training lightweight text classifiers using dynamically generated supervision from an LLM. Our method employs an iterative, agentic loop in which the LLM curates training data, analyzes model successes and failures, and synthesizes targeted examples to address observed errors. This closed-loop generation and evaluation process progressively improves data quality and adapts it to the downstream classifier and task. Across four widely used benchmarks, our approach consistently outperforms standard zero and few-shot baselines. These results indicate that LLMs can serve effectively as data curators, enabling accurate and efficient classification without the operational cost of large-model deployment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 15 of its 30 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

15 of 30 references.

References · 15

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  3. 2019Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approachcited by 299
  4. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 209
  5. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  6. 2021Want To Reduce Labeling Cost? GPT-3 Can Helpcited by 196
  7. 2019Text Classification Algorithms: A Surveycited by 163
  8. 2022Efficient Few-Shot Learning Without Promptscited by 135
  9. 2023Text Classification via Large Language Modelscited by 104
  10. 2021Improving and Simplifying Pattern Exploiting Trainingcited by 97
  11. 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
  12. 2019Zero-shot Text Classification With Generative Language Modelscited by 55
3 more
  1. 2023Large Language Models Are Zero-Shot Text Classifierscited by 35
  2. 2025EuroBERT: Scaling Multilingual Encoders for European Languagescited by 28
  3. 2025GLiClass: Generalist Lightweight Model for Sequence Classification Taskscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Zero-Shot Text Classification with Self-Training
  2. 2024Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data
  3. 2023Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
  4. 2025Don't Just Demo, Teach Me the Principles: A Principle-Based Multi-Agent Prompting Strategy for Text Classification
  5. 2026A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification
  6. 2023Agent Instructs Large Language Models to be General Zero-Shot Reasoners
  7. 2023ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval
  8. 2025IMPROVE: Iterative Model Pipeline Refinement and Optimization Leveraging LLM Experts