works on

From the 3 of 19 linked papers with an AI index.

collaborators

19 papers

cs.CY2026

Programming Language Policy as an AI Literacy Equity Problem: A 15-Nation Comparative Analysis

Adrian-Marius Dumitran, Iulia-Maria Popescu

The paper compares secondary computer science curricula in fifteen countries, revealing that many students lack formal programming exposure and that Python dominates general educat…

cs.CY2026

The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students

Alexis Popovici, Andrei Ionascu, Adrian-Marius Dumitran

The paper audits four large language model tutors on their responses to history questions about the 1989 Romanian Revolution for students of different ethnic and socioeconomic back…

cs.CL2026

Automated Textbook Auditing with Multi-Agent LLM Systems

Ciprian Cristescu, Adrian-Marius Dumitran, Angela-Liliana Dumitran +1

The paper introduces AI Textbook Auditor, a modular multi‑agent pipeline that uses large language models to automatically detect factual, technical, and grammatical errors in textb…

cs.CL2026

Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems

Heming Fu, Shan Lin, Qianqian Xie +1

When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what…

cs.HC2026

Block-Based Pathfinding: A Minecraft System for Visualizing Graph Algorithms

Luca-Stefan Pirvu, Bogdan-Alexandru Maciuca, Andrei-Ciprian Rabu +1

Graph theory is a cornerstone of Computer Science education, yet entry-level students often struggle to map abstract node-edge relationships to practical applications. This paper p…

cs.CL2026

MuTSE: A Human-in-the-Loop Multi-use Text Simplification Evaluator

Rares-Alexandru Roscan, Gabriel Petre1, Adrian-Marius Dumitran +1

As Large Language Models (LLMs) become increasingly prevalent in text simplification, systematically evaluating their outputs across diverse prompting strategies and architectures…