# CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring

arXiv: https://arxiv.org/abs/2505.13965 · HTML: https://mlsanity.com/paper/2505.13965/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 59 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 29 of 29)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers](https://mlsanity.com/paper/2502.20379/) (2025)
- [A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges](https://mlsanity.com/paper/2412.11936/) (2024)
- [On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation](https://mlsanity.com/paper/2205.03835/) (2022)
- [Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality](https://mlsanity.com/paper/2410.04780/) (2024)
- [Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs](https://mlsanity.com/paper/2401.06431/) (2024)
- [Can Large Language Models Automatically Score Proficiency of Written Essays?](https://mlsanity.com/paper/2403.06149/) (2024)
- [Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook](https://mlsanity.com/paper/2402.19348/) (2024)
- [Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring](https://mlsanity.com/paper/2404.04941/) (2024)
- [Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning](https://mlsanity.com/paper/2502.02871/) (2025)
- [SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning](https://mlsanity.com/paper/2502.12520/) (2025)
- [Automated essay scoring with string kernels and word embeddings](https://mlsanity.com/paper/1804.07954/) (2018)
- [MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2502.11051/) (2025)
- [Bringing Generative AI to Adaptive Learning in Education](https://mlsanity.com/paper/2402.14601/) (2024)
- [MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection](https://mlsanity.com/paper/2503.18132/) (2025)
- [Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring](https://mlsanity.com/paper/2407.18328/) (2024)
- [Evolution of AI in Education: Agentic Workflows](https://mlsanity.com/paper/2504.20082/) (2025)
- [Automated assessment of non-native learner essays: Investigating the role of linguistic features](https://mlsanity.com/paper/1612.00729/) (2016)
- [Are Large Language Models Good Essay Graders?](https://mlsanity.com/paper/2409.13120/) (2024)
- [Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition__Taking TOEFL Independent Writing Task for Example](https://mlsanity.com/paper/2401.03401/) (2024)
- [Unveiling the Tapestry of Automated Essay Scoring: A Comprehensive Investigation of Accuracy, Fairness, and Generalizability](https://mlsanity.com/paper/2401.05655/) (2024)
- [TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment](https://mlsanity.com/paper/2409.19894/) (2024)
- [Grounded Answers for Multi-agent Decision-making Problem through Generative World Model](https://mlsanity.com/paper/2410.02664/) (2024)
- [Position: LLMs Can be Good Tutors in English Education](https://mlsanity.com/paper/2502.05467/) (2025)

## Built on by (most cited first, 7 of 7)

- [DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning](https://mlsanity.com/paper/2509.23883/) (2025)
- [Agent-as-a-Judge](https://mlsanity.com/paper/2601.05111/) (2026)
- [Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework](https://mlsanity.com/paper/2602.19549/) (2026)
- [Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval](https://mlsanity.com/paper/2602.19961/) (2026)
- [Agreement Between Large Language Models and Human Raters in Essay Scoring: A Research Synthesis](https://mlsanity.com/paper/2512.14561/) (2025)
- [Specialists or Generalists? Multi-Agent and Single-Agent LLMs for Essay Grading](https://mlsanity.com/paper/2601.22386/) (2026)
- [MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring](https://mlsanity.com/paper/2606.06754/) (2026)

## Abstract (arXiv)

Automated Essay Scoring (AES) is crucial for modern education, particularly with the increasing prevalence of multimodal assessments. However, traditional AES methods struggle with evaluation generalizability and multimodal perception, while even recent Multimodal Large Language Model (MLLM)-based approaches can produce hallucinated justifications and scores misaligned with human judgment. To address the limitations, we introduce CAFES, the first collaborative multi-agent framework specifically designed for AES. It orchestrates three specialized agents: an Initial Scorer for rapid, trait-specific evaluations; a Feedback Pool Manager to aggregate detailed, evidence-grounded strengths; and a Reflective Scorer that iteratively refines scores based on this feedback to enhance human alignment. Extensive experiments, using state-of-the-art MLLMs, achieve an average relative improvement of 21% in Quadratic Weighted Kappa (QWK) against ground truth, especially for grammatical and lexical diversity. Our proposed CAFES framework paves the way for an intelligent multimodal AES system. The code will be available upon acceptance.