# MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring

arXiv: https://arxiv.org/abs/2606.06754 · HTML: https://mlsanity.com/paper/2606.06754/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 18 of 18)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation](https://mlsanity.com/paper/2205.03835/) (2022)
- [Evaluating Scoring Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2506.22316/) (2025)
- [Can Large Language Models Automatically Score Proficiency of Written Essays?](https://mlsanity.com/paper/2403.06149/) (2024)
- [Many Hands Make Light Work: Using Essay Traits to Automatically Score Essays](https://mlsanity.com/paper/2102.00781/) (2021)
- [Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring](https://mlsanity.com/paper/2305.16826/) (2023)
- [Enhancing Multi-Agent Debate System Performance via Confidence Expression](https://mlsanity.com/paper/2509.14034/) (2025)
- [Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards](https://mlsanity.com/paper/2409.17472/) (2024)
- [Are Large Language Models Good Essay Graders?](https://mlsanity.com/paper/2409.13120/) (2024)
- [LCES: Zero-shot Automated Essay Scoring via Pairwise Comparisons Using Large Language Models](https://mlsanity.com/paper/2505.08498/) (2025)
- [CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring](https://mlsanity.com/paper/2505.13965/) (2025)
- [Says Who? Effective Zero-Shot Annotation of Focalization](https://mlsanity.com/paper/2409.11390/) (2024)

## Abstract (arXiv)

We present MADRAG, a training-free framework for analytic essay scoring that combines multi-agent reasoning with retrieval-augmented grounding. Unlike standard LLM-as-judge approaches, which are prone to bias and unstable scoring, MADRAG decomposes evaluation into an interactive process: an Advocate identifies strengths, a Skeptic critiques weaknesses, and a Judge aggregates their arguments into a final score. Crucially, the Judge is augmented with rubric-aligned exemplar retrieval, enabling calibration through comparison with scored examples. Our results show that MADRAG significantly outperforms prompt-based baselines while approaching the performance of supervised systems without requiring task-specific training. Ablation studies demonstrate that retrieval drives calibration gains, while debate improves reasoning on higher-level traits. Our findings highlight the complementary roles of structured interaction and external memory in reliable LLM-based evaluation.