ARAMIS: A web tool integrated with open-source LLM for supporting the correction of undergraduate students' theses

2026-04-12 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning · Depth: Advanced, quick

Summary

ARAMIS is an integrated web tool utilizing open-source Large Language Models (LLMs) to facilitate the correction of undergraduate final papers (TCC) written in Portuguese. This multi-agent system addresses three core pillars: grammatical correction, logical coherence, and methodological rigor, providing users with structured reviews tailored to each selected area. Designed to streamline the often costly and time-consuming academic paper review process, ARAMIS aims to support researcher training. Despite being in an experimental stage, the tool demonstrated excellent usability, achieving a System Usability Scale (SUS) score of 90.5 out of 100 in initial tests.

Key takeaway

For academic institutions and educators overseeing undergraduate final papers in Portuguese, ARAMIS offers a promising approach to automate and standardize the review process. Consider piloting similar LLM-based tools to reduce review costs and provide consistent, structured feedback on grammar, coherence, and methodology, potentially improving student paper quality and reviewer efficiency.

Key insights

ARAMIS is an open-source LLM-based multi-agent tool for reviewing Portuguese undergraduate final papers.

Principles

• Automated review can enhance researcher training.
• Structured feedback improves paper correction.

Method

ARAMIS employs a multi-agent architecture with open-source LLMs to review papers based on grammar, coherence, and methodology, providing structured feedback for each pillar.

In practice

• Apply LLMs for academic paper review.
• Structure feedback by review pillar.

Topics

• ARAMIS
• Open-source LLM
• Academic Paper Review
• Undergraduate TCC
• Portuguese Language Processing

Best for: AI Scientist, NLP Engineer, Research Scientist

Related on AIssential

• Intelligence Is Not the Bottleneck: Validating an LLM First-Pass Manuscript Score Against Peer-Review Outcomes — An LLM-based system can accurately predict peer-review outcomes and provide structured feedback for academic manuscripts.
• Improving the academic workflow: Introducing two AI agents for better figures and peer review — AI agents can automate complex academic tasks like figure generation and peer review, improving efficiency and quality.
• FlexQwen: Exploring Hybrid Objectives and Text Originality for Portuguese — Hybrid objectives and text originality can enhance efficient LLM pre-training for low-resource languages.
• MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese — Math-PT is the first native Portuguese benchmark for LLM mathematical reasoning, revealing performance gaps in open-ended and visual problems.
• The Crutch or the Ceiling? How Different Generations of LLMs Shape EFL Student Writings — Advanced LLMs improve EFL writing metrics but may mask true ability and hinder deep coherence.
• Beyond Grading Accuracy: Exploring Alignment of TAs and LLMs — Open-source LLMs can effectively grade UML class diagrams with high per-criterion accuracy, aiding TAs.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.