International Peer-Reviewed Journal•Open Access•ISSN 2456-8880
irejournals@gmail.com•+91-7433024337

Home / Current Issue / Paper 1711930

1711930 Vol 9 · Issue 5 Download Paper

Design and Implementation of a Multi-Modal, Agentic Code Companion System (ICC) using Fine-Tuned Code LLMs and Structured Visualization

Kunal Kumar Nath Samridh Chauhan Tanmay Jadhav Pranit Virkar

Subject area: Science,Engineering and Technology  ·  Area of research: Education

DOI: 10.64388/IREV9I5-1711930

Abstract

This paper proposes the architectural design and implementation strategy for the Intelligent Code Companion (ICC) system, a novel platform engineered to process multi- modal code queries (text and image) and generate comprehensive, structured outputs. The core innovation lies in a hybrid LLM Agent architecture that coordinates specialized tools, specifically Optical Character Recognition (OCR) for handling photographed code inputs and a Structured Output Generator for creating dynamic, animated flowcharts. The system deviates from using underpowered base models, advocating instead for the instruction fine- tuning of a high-performing yet resource- efficient model, such as the StarCoder2-3B model, utilizing Quantized Low-rank Adaptation (QLoRA).

Keywords

Large Language Models, Code Generation, Multi-Modality, Optical Character Recognition (OCR), Agentic Systems, Structured Output, QLoRA Fine-Tuning, Full- Stack Architecture, FastAPI, Perplexity UI.

References

[1] Perplexity AI. (2025). Perplexity AI: The Answer Engine Philosophy.

[2] BigCode Project. (2024). StarCoder2: The Next Generation of Code LLMs. arXiv preprint.

[3] Black, S. et al. (2022). The Stack: A Large- Scale Dataset of Permissively Licensed Source Code. arXiv preprint.

[4] LangGraph Team. (2024). Agent Architecture: Planning and Memory in LLM Systems.

[5] Chen, B. (2023). Retrieval-Augmented Generation (RAG) for Contextual Code Synthesis. IEEE Software.

[6] OWASP Foundation. (2023). A Guide to Parameterized Queries and SQL Injection Prevention.

[7] Dettmers, T. et al. (2023). QLoRA: Efficient Finetuning of Quantized LLMs. arXiv preprint.

[8] NVIDIA & BigCode. (2024).

[9] StarCoder2 Performance Benchmarks: Small Model Viability. Technical Brief.

[10] Baidu Research. (2023). PaddleOCR: Deep Learning for Layout-Aware Text Recognition.

[11] Alqahtani, S. et al. (2023). The Impact of AI on Personalized Learning. Journal of Educational Technology.

How to cite this paper

Kunal Kumar Nath, Samridh Chauhan, Tanmay Jadhav, Pranit Virkar "Design and Implementation of a Multi-Modal, Agentic Code Companion System (ICC) using Fine-Tuned Code LLMs and Structured Visualization" Iconic Research And Engineering Journals Volume 9 Issue 5 2025 Page 659-669 https://doi.org/10.64388/IREV9I5-1711930
Kunal Kumar Nath, Samridh Chauhan, Tanmay Jadhav, Pranit Virkar "Design and Implementation of a Multi-Modal, Agentic Code Companion System (ICC) using Fine-Tuned Code LLMs and Structured Visualization" Iconic Research And Engineering Journals, vol. 9, no. 5, Nov. 2025, doi: https://doi.org/10.64388/IREV9I5-1711930
Kunal Kumar Nath, Samridh Chauhan, Tanmay Jadhav, Pranit Virkar (2025). Design and Implementation of a Multi-Modal, Agentic Code Companion System (ICC) using Fine-Tuned Code LLMs and Structured Visualization. Iconic Research And Engineering Journals, 9(5). doi: https://doi.org/10.64388/IREV9I5-1711930
Kunal Kumar Nath, Samridh Chauhan, Tanmay Jadhav, Pranit Virkar "Design and Implementation of a Multi-Modal, Agentic Code Companion System (ICC) using Fine-Tuned Code LLMs and Structured Visualization" Iconic Research And Engineering Journals, vol. 9, no. 5, Nov. 2025. Crossref, https://doi.org/10.64388/IREV9I5-1711930
@article{1711930,
      author = {Kunal Kumar Nath, Samridh Chauhan, Tanmay Jadhav, Pranit Virkar},
      title = {Design and Implementation of a Multi-Modal, Agentic Code Companion System (ICC) using Fine-Tuned Code LLMs and Structured Visualization},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {5},
      pages = {659-669},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1711930.pdf},
      abstract = {This paper proposes the architectural design and implementation strategy for the Intelligent Code Companion (ICC) system, a novel platform engineered to process multi- modal code queries (text and image) and generate comprehensive, structured outputs. The core innovation lies in a hybrid LLM Agent architecture that coordinates specialized tools, specifically Optical Character Recognition (OCR) for handling photographed code inputs and a Structured Output Generator for creating dynamic, animated flowcharts. The system deviates from using underpowered base models, advocating instead for the instruction fine- tuning of a high-performing yet resource- efficient model, such as the StarCoder2-3B model, utilizing Quantized Low-rank Adaptation (QLoRA).},
      keywords = {Large Language Models, Code Generation, Multi-Modality, Optical Character Recognition (OCR), Agentic Systems, Structured Output, QLoRA Fine-Tuning, Full- Stack Architecture, FastAPI, Perplexity UI.},
      month = {November},
      doi = {https://doi.org/10.64388/IREV9I5-1711930}
  }