Publicerad: 2024-11-05
Master Thesis - Engineering Report Generator Using Generative AI
.
Transport is at the core of modern society. Imagine using your expertise to shape sustainable transport and infrastructure solutions for the future? If you seek to make a difference on a global scale, working with next-gen technologies and the sharpest collaborative teams, then we could be a perfect match.
Thesis Background
Engineering reports are essential for documenting and communicating project findings, analysis, and recommendations. However, the process of writing these reports can be time-consuming and challenging. This thesis aims to develop an Engineering Report Agent, a multi-agent application powered by large language models, that assists in the construction and improvement of engineering reports. By leveraging existing agents and integrating their functionalities, the goal is to create a powerful tool that can automate parts of the report writing process.
In the field of report generation, previous research has primarily focused on the medical sector [1] [2]. However, there have also been studies exploring the automatic generation of government reports using generative AI approaches [3]. These research efforts offer valuable insights and can serve as valuable references for the development of the Engineering Report Agent.
What will you do
The primary objective of this thesis is to construct an agent that can assist in writing engineering reports. The agent should be capable of generating parts of the report, thereby enhancing the efficiency and quality of the report writing process. The thesis students will develop a multi-agent application that integrates various agents, both new and existing ones, to leverage their functionalities and improve the overall report writing experience. By harnessing the power of multiple agents, the goal is to create a comprehensive and efficient tool that can significantly aid engineers in constructing high-quality engineering reports.
If time permits, the performance of the Engineering Report Agent can be compared to a human-written report. Previous research has shown promising results for Generative AI (GPT-3.5) in report generation, but it did not outperform human-written reports [4]. This optional goal can provide valuable insights into the capabilities and limitations of the agent. The proposed Engineering Report Agent, which leverages multi-agent technology, aligns with the current trends in autonomous multi-agent systems powered by Large Language Models [5]. By integrating existing agents and developing new ones, the agent aims to streamline the construction and improvement of engineering reports by automating parts of the report writing process. While challenges such as hallucination need to be addressed, we believe that this thesis topic is highly relevant and has the potential to greatly assist engineers in generating high-quality engineering reports.
Who are you?
We are looking for highly motivated students with a passion for emerging technologies and AI, and with the ability to drive the work forward by being proactive, curious, and persistent. You should have strong analytical and programing skills.
The key qualifications include:
* Master students in Engineering Physics, Data Science, Mathematics, or related field
* Proficiency in Python programming skills
* Prior experience with Generative AI is a plus
Information
The last application date is the 16th of November.
Project start: January 2025.
Contact persons:
Elias Sörstrand, (Industrial Supervisor), Volvo Group Trucks Technology, Göteborg, Sweden, E-mail: elias.sorstrand.2@consultant.volvo.com
Masoom Kumar, (Industrial Supervisor), Volvo Group Trucks Technology, Bangalore, India, E-mail: masoom.kumar@volvo.com
Bibliography
[1] Dantas Costa, E., Carneiro, J. A., Guerra Zancan, B. A., Gaêta-Araujo, H., Oliveira-Santos, C., Macedo, A. A., & Tirapelli, C. (2024). Potential of artificial intelligence to generate health research reports of decayed, missed and restored teeth. Odovtos International Journal of Dental Sciences, 26(2), 14-19.
[2] Tiwari, V., Bapat, K., Shrimali, K. R., Singh, S. K., Tiwari, B., Jain, S., & Sharma, H. K. (2021, August). Automatic generation of chest x-ray medical imaging reports using lstm-cnn. In Proceedings of the international conference on data science, machine learning and artificial intelligence (pp. 80-85).
[3] Gupta, R., Pandey, G., & Pal, S. K. (2024). Automating Government Report Generation: A Generative AI Approach for Efficient Data Extraction, Analysis, and Visualization. Digital Government: Research and Practice.
[4] Pinto, D. S., Noronha, S. M., Saigal, G., Quencer, R. M., & Noronha, S. (2024). Comparison of an AI-Generated Case Report With a Human-Written Case Report: Practical Considerations for AI-Assisted Medical Writing. Cureus, 16(5).
[5] Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., ... & Zhang, X. (2024). Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680.
We do not accept applications via mail.
Who we are and what we believe in
Our focus on Inclusion, Diversity, and Equity allows each of us the opportunity to bring our full authentic self to work and thrive. Every day, across the globe, our trucks, buses, engines, construction equipment, and solutions make modern life possible. We are almost 100,000 people empowered to shape the future landscape of efficient, safe and sustainable transport solutions.
Transport is at the core of modern society. Imagine using your expertise to shape sustainable transport and infrastructure solutions for the future? If you seek to make a difference on a global scale, working with next-gen technologies and the sharpest collaborative teams, then we could be a perfect match.
Thesis Background
Engineering reports are essential for documenting and communicating project findings, analysis, and recommendations. However, the process of writing these reports can be time-consuming and challenging. This thesis aims to develop an Engineering Report Agent, a multi-agent application powered by large language models, that assists in the construction and improvement of engineering reports. By leveraging existing agents and integrating their functionalities, the goal is to create a powerful tool that can automate parts of the report writing process.
In the field of report generation, previous research has primarily focused on the medical sector [1] [2]. However, there have also been studies exploring the automatic generation of government reports using generative AI approaches [3]. These research efforts offer valuable insights and can serve as valuable references for the development of the Engineering Report Agent.
What will you do
The primary objective of this thesis is to construct an agent that can assist in writing engineering reports. The agent should be capable of generating parts of the report, thereby enhancing the efficiency and quality of the report writing process. The thesis students will develop a multi-agent application that integrates various agents, both new and existing ones, to leverage their functionalities and improve the overall report writing experience. By harnessing the power of multiple agents, the goal is to create a comprehensive and efficient tool that can significantly aid engineers in constructing high-quality engineering reports.
If time permits, the performance of the Engineering Report Agent can be compared to a human-written report. Previous research has shown promising results for Generative AI (GPT-3.5) in report generation, but it did not outperform human-written reports [4]. This optional goal can provide valuable insights into the capabilities and limitations of the agent. The proposed Engineering Report Agent, which leverages multi-agent technology, aligns with the current trends in autonomous multi-agent systems powered by Large Language Models [5]. By integrating existing agents and developing new ones, the agent aims to streamline the construction and improvement of engineering reports by automating parts of the report writing process. While challenges such as hallucination need to be addressed, we believe that this thesis topic is highly relevant and has the potential to greatly assist engineers in generating high-quality engineering reports.
Who are you?
We are looking for highly motivated students with a passion for emerging technologies and AI, and with the ability to drive the work forward by being proactive, curious, and persistent. You should have strong analytical and programing skills.
The key qualifications include:
* Master students in Engineering Physics, Data Science, Mathematics, or related field
* Proficiency in Python programming skills
* Prior experience with Generative AI is a plus
Information
The last application date is the 16th of November.
Project start: January 2025.
Contact persons:
Elias Sörstrand, (Industrial Supervisor), Volvo Group Trucks Technology, Göteborg, Sweden, E-mail: elias.sorstrand.2@consultant.volvo.com
Masoom Kumar, (Industrial Supervisor), Volvo Group Trucks Technology, Bangalore, India, E-mail: masoom.kumar@volvo.com
Bibliography
[1] Dantas Costa, E., Carneiro, J. A., Guerra Zancan, B. A., Gaêta-Araujo, H., Oliveira-Santos, C., Macedo, A. A., & Tirapelli, C. (2024). Potential of artificial intelligence to generate health research reports of decayed, missed and restored teeth. Odovtos International Journal of Dental Sciences, 26(2), 14-19.
[2] Tiwari, V., Bapat, K., Shrimali, K. R., Singh, S. K., Tiwari, B., Jain, S., & Sharma, H. K. (2021, August). Automatic generation of chest x-ray medical imaging reports using lstm-cnn. In Proceedings of the international conference on data science, machine learning and artificial intelligence (pp. 80-85).
[3] Gupta, R., Pandey, G., & Pal, S. K. (2024). Automating Government Report Generation: A Generative AI Approach for Efficient Data Extraction, Analysis, and Visualization. Digital Government: Research and Practice.
[4] Pinto, D. S., Noronha, S. M., Saigal, G., Quencer, R. M., & Noronha, S. (2024). Comparison of an AI-Generated Case Report With a Human-Written Case Report: Practical Considerations for AI-Assisted Medical Writing. Cureus, 16(5).
[5] Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., ... & Zhang, X. (2024). Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680.
We do not accept applications via mail.
Who we are and what we believe in
Our focus on Inclusion, Diversity, and Equity allows each of us the opportunity to bring our full authentic self to work and thrive. Every day, across the globe, our trucks, buses, engines, construction equipment, and solutions make modern life possible. We are almost 100,000 people empowered to shape the future landscape of efficient, safe and sustainable transport solutions.