From Advocacy to Judgment: Training-Free Analytic Essay Scoring with Multi-Agent Debate and Exemplar Retrieval

Keywords: Automated Essay Scoring, Large Language Models, Multi-Agent Debate, Retrieval-Augmented Generation, LLM-as-a-Judge, Calibration Bias, Educational NLP

Abstract: Automated Essay Scoring (AES) is shifting from feature-engineering to LLMs, yet current training-free approaches struggle with calibration, often exhibiting a "middle-score bias" that fails to distinguish between exceptional and weak writings. In this work, we introduce MADRAG (Multi-Agent Debate with Retrieval-Augmented Generation), a training-free framework designed to achieve the reliability of supervised models without the need for labeled training data. MADRAG decomposes the scoring process into a multi-agent interaction: an Advocate highlights essay strengths, a Skeptic critiques weaknesses, and a Judge synthesizes these arguments to assign a score. Crucially, we augment the Judge with RAG mechanism that retrieves rubric-aligned exemplar essays spanning the full score range, grounding the debate in concrete evidence. Evaluating our approach on the ASAP dataset for analytic trait scoring, we demonstrate that MADRAG significantly outperforms existing prompt-based LLM baselines and achieves performance competitive with state-of-the-art supervised models.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: AI / LLM Agents, NLP Applications, Generation, Resources and Evaluation, Human-Centered NLP

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data analysis

Languages Studied: English

Submission Number: 7122