MIPTS: A Multimodal Physics Tutoring System Synergizing Hybrid RAG and Autonomous Agents

DOI

10.2991/978-94-6239-691-3_14How to use a DOI?

Keywords

Multimodal Physics Tutoring; Hybrid RAG; Knowledge Graphs; Autonomous Agents; Symbolic Reasoning; Physics Education

Abstract

Large Language Models (LLMs) have shown promise in educational applications, yet their direct use in physics tutoring is hindered by hallucinations, unstable symbolic computation, and insufficient modeling of physics knowledge structures. To address these limitations, this paper proposes a Multimodal Intelligent Physics Tutoring System (MIPTS) based on a Hybrid Retrieval-Augmented Generation (RAG) framework. The system integrates knowledge graphs, deep document understanding, and autonomous agents to support structured reasoning and teaching-oriented feedback in physics problem solving. An intention-driven dual-channel architecture separates latent tool-augmented reasoning from low-latency Socratic guidance, improving both reliability and instructional interpretability. Case studies on six university-level physics problems demonstrate that MIPTS achieves better physical consistency, reasoning transparency, and pedagogical rigor than general-purpose LLM-based systems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xiangyu Yang
AU  - Can He
AU  - Meng Zhang
PY  - 2026
DA  - 2026/05/31
TI  - MIPTS: A Multimodal Physics Tutoring System Synergizing Hybrid RAG and Autonomous Agents
BT  - Proceedings of the 2026 5th International Conference on Educational Innovation and Multimedia Technology (EIMT 2026)
PB  - Atlantis Press
SP  - 121
EP  - 131
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-691-3_14
DO  - 10.2991/978-94-6239-691-3_14
ID  - Yang2026
ER  -