# Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring

arXiv: https://arxiv.org/abs/2608.23814 · HTML: https://mlsanity.com/paper/2608.23814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [Exploring LLM Prompting Strategies for Joint Essay Scoring and Feedback Generation](https://mlsanity.com/paper/2404.15845/) (2024)
- [CARROT: A Cost Aware Rate Optimal Router](https://mlsanity.com/paper/2502.03261/) (2025)
- [Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring](https://mlsanity.com/paper/2404.04941/) (2024)
- [Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs](https://mlsanity.com/paper/2410.14202/) (2024)
- [AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.19251/) (2024)
- [Is GPT-4 Alone Sufficient for Automated Essay Scoring?: A Comparative Judgment Approach Based on Rater Cognition](https://mlsanity.com/paper/2407.05733/) (2024)
- [Can We Afford The Perfect Prompt? Balancing Cost and Accuracy with the Economical Prompting Index](https://mlsanity.com/paper/2412.01690/) (2024)
- [Do We Need a Detailed Rubric for Automated Essay Scoring using Large Language Models?](https://mlsanity.com/paper/2505.01035/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) demonstrate strong capabilities in automated essay scoring (AES), but contemporary approaches typically employ fixed prompt selection, failing to address operational cost concerns and evolving optimal configurations. We propose a novel cost-aware approach that treats each prompt type as an arm in a multi-armed bandit (MAB) controller, enabling adaptive selection of optimal prompting strategies during inference. Our experiments on IELTS Writing Task 2 essays show that the MAB framework achieves comparable scoring accuracy to exhaustive grid search while reducing LLM calls by 78.4% to find the best grading approach. We implemented four distinct grading recipes (multi-step vs. single-step assessment, with vs. without calibration examples) and found that the multi-step approach with examples achieves the highest accuracy. By tracking token usage and latency alongside agreement metrics, we produce the first cost-reliability learning curves for essay scoring, providing actionable insights for educational technology platforms that must balance operational costs against assessment validity. This work represents the first application of online control mechanisms to adaptively select prompting strategies in AES, transforming prompt selection from an offline hyperparameter optimization problem into an efficient online learning task.