Akash Agrawal

I am a postdoctoral researcher at Carnegie Mellon University, specializing in integrating AI into engineering design grammars to enhance adaptability and efficiency. I recently completed my Ph.D. under Chris McComb, concentrating on the intersection of AI and mechanical engineering. My research involved developing RL frameworks to address complex challenges like design space exploration and intelligent manufacturing. I also hold an M.S. in Engineering Design from Penn State, a B.E. in Mechanical Engineering from BITS, Pilani and have industry experience as a design engineer at Johnson Controls.

I am actively seeking research roles in environments that value both rigorous research and its transition into product development.

Dive into my experiences

Ph.D. Mechanical Engineering

M.S.
Engineering
Design

Design Engineer
Building Technologies &
Solutions

B.E. (Hons.) Mechanical Engineering

Publications

1. Agrawal, A., Shea, K., Stankovic, T., Cagan, J., McComb, C. (2025). “Expanding the Generative Power of LLMs for Engineering Design through Formal Grammars”, preparing for Journal of Computing and Information Science in Engineering

2. Agrawal, A., & McComb, C. (2024). Adaptive Learning of Design Strategies over Non-Hierarchical Multi-Fidelity Models via Policy Alignment, in review at JMD, preprint available at DOI: 10.48550/arXiv.2411.10841

3. Agrawal, A. et al. (2024) To Centralize or Decentralize? Examining Cyber-Physical Control on the Manufacturing Shop Floor, in review at JCISE, preprint available at DOI: 10.31224/3567

4. Agrawal, A., & McComb, C. (2024). Symmetry Heuristics for Stable RL Design Agents, In: Gero, J.S. (eds) Design Computing and Cognition’24. DCC 2024. Springer, Cham. DOI: 10.1007/978-3-031-71922-6_4

5. Agrawal, A., & McComb, C. (2023). Reinforcement Learning for Efficient Design Space Exploration With Variable Fidelity Analysis Models. Journal of Computing and Information Science in Engineering, 23(4), 041004. DOI: 10.1115/1.4056297

6. Agrawal, A., & McComb, C. (2022). Comparing strategies for visualizing the high-dimensional exploration behavior of CPS design agents. In 2022 IEEE Workshop on Design Automation for CPS and IoT (DESTION) (pp. 64-69). IEEE. DOI: 10.1109/DESTION56136.2022.00017

7. Agrawal, A. et al. (2021). A multi-agent reinforcement learning framework for intelligent manufacturing with autonomous mobile robots. Proceedings of the Design Society, 1, 161-170. DOI: 10.1017/pds.2021.17

8. Song, B., Meinzer, E., Agrawal, A., & McComb, C. (2020). Topic modeling and sentiment analysis of social media data to drive experiential redesign. In IDETC-CIE (Vol. 84003, p. V11AT11A019). American Society of Mechanical Engineers. DOI: 10.1115/DETC2020-22567

Intellectual Property

1. Awasthi, M., Sahu, K. D., & Agrawal, A. R. (2021). Universal adapter assembly for valve actuator, U.S. Patent No. 10,962,137. Washington, DC: U.S. Patent and Trademark Office.

2. Patil, V. A., Agrawal, A. R., Jagatheesan, A., Rockhold, J. S., Patil, P. G., & Massar, M. M. (2024). High velocity wind-driven rain louver, U.S. Patent No. 11,946,664. Washington, DC: U.S. Patent and Trademark Office.

3. Mishra, A., Ranjan, T., Agrawal, A., & Kannan, S. (2023). Thermoelectric heat exchanger for an HVAC system, U.S. Patent Application No. 18/095,415.