Abstract: Artificial intelligence and cognitive science technologies are combined to develop a problem-solving system of Chinese arithmetic words in elementary schools. Students can input an ...

Abstract: Solving mathematical (math) word problems (MWP) automatically is a challenging research problem in natural language processing, machine learning, and education (learning) technology domains, ...

This study investigated the developmental relationship between children's mental representations of the arithmetic change problem structure (the change problem schema) and their use of part-whole ...

Solving arithmetic word problems requires individuals to create a correct mental representation, and this involves both text processing and number processing. The latter comprises understanding the ...

This study investigates the relationship between skills that underpin mathematical word problems and those that underpin numerical operations, such as addition, subtraction division and multiplication ...

large-scale language models (LLMs), such as OpenAI's GPT-4, has advanced and wide-ranging capabilities, such as generating natural sentences and solving various problems. However, even in elementary ...

Mathematical language processing and problem solving represent a confluence of artificial intelligence, natural language processing and symbolic reasoning, aiming to bridge the gap between human ...

The artificial intelligence community celebrated a remarkable milestone in 2025 when both Google DeepMind and OpenAI systems ...

This repository demonstrates a multi-agent system that solves grade-school math problems using a collection of “tools.” The system relies on LLM-based agents (via Azure OpenAI or OpenAI) that: ...