Shreedhar Jangam

About Me

Hi 👋🏼 I am an M.S. student in Robotics at the Carnegie Mellon University Robotics Institute, interested in building safe and adaptive robotic systems that can operate reliably under uncertainty.

Previously, I completed my B.S. in Computer Science with a Minor in Statistics at UC Santa Cruz, where I was fortunate to work with Prof. Leilani Gilpin at the AEIA Lab on LLM trustworthiness and interpretability, and Prof. Xin (Eric) Wang at the ERIC Lab on reasoning-model and VLA safety evaluation. I also conducted research at the National Renewable Energy Laboratory, developing physics-informed and interpretable models of nonlinear dynamical systems. Outside of research, I enjoy backpacking and practicing my wilderness EMT skills.

Research Interests

I’m excited by how embodied systems can reason about the world, learn interpretable dynamics, and act safely under uncertainty. This interest is motivated by questions of how language-based reasoning can be grounded in physical systems, and how structured dynamics can support reliable decision making. Broadly, my interests are in interpretable autonomy, grounded world models, and VLA-based reasoning monitors that help robots maintain reliable internal beliefs and execute robust manipulation behaviors.

Publications

ICLR 2026

SafePro: Evaluating the Safety of Professional-Level AI Agents

Kaiwen Zhou, Shreedhar Jangam, Ashwin Nagarajan, Tejas Polu, Suhas Oruganti, Chengzhi Liu, Ching-Chen Kuo, Yuting Zheng, Sravana Narayanaraju, Xin Eric Wang

Website PDF Accepted

@article{Zhou2026SafePro,
  title={SafePro: Evaluating the Safety of Professional-Level AI Agents},
  author={Zhou, Kaiwen and Jangam, Shreedhar and Nagarajan, Ashwin and Polu, Tejas and Oruganti, Suhas and Liu, Chengzhi and Kuo, Ching-Chen and Zheng, Yuting and Narayanaraju, Sravana and Wang, Xin Eric},
  journal={arXiv preprint arXiv:2601.06663},
  year={2026}
}

IJCNLP-AACL 2025

The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1

Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao, Shreedhar Jangam, Jayanth Srinivasa, Gaowen Liu, Dawn Song, Xin Eric Wang

Website PDF Accepted

@article{Zhou2025HiddenRisks,
  title={The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1},
  author={Zhou, Kaiwen and Liu, Chengzhi and Zhao, Xuandong and Jangam, Shreedhar and Srinivasa, Jayanth and Liu, Gaowen and Song, Dawn and Wang, Xin Eric},
  journal={arXiv preprint arXiv:2502.12659},
  year={2025}
}

arXiv

Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations

Shiyuan Huang, Siddarth Mamidanna, Shreedhar Jangam, Yilun Zhou, Leilani H. Gilpin

PDF Preprint

@article{Huang2023LLMExplain,
  title={Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations},
  author={Huang, Shiyuan and Mamidanna, Siddarth and Jangam, Shreedhar and Zhou, Yilun and Gilpin, Leilani H.},
  journal={arXiv preprint arXiv:2310.11207},
  year={2023}
}

News

2026

JanuaryI submitted a paper introducing SafePro, a benchmark for evaluating the safety failures in long-horizon AI agents [Link]

▶ Show past events

2025

DecemberI completed my internship at NREL (now NLR) and presented my work on PIML: system identification and data-driven control.
JuneI began my internship at National Renewable Energy Laboratory in Golden, Colorado.
FebruaryI submitted a paper on reasoning model (R1 and o3mini) safety. [Link]
JanuaryI was awarded an honorable mention for the CRA Outstanding Undergraduate Researcher Award. [Link]

2024

AugustI finished my research internship at ERAU and presented our research on swarm communication and formation control. [Link]
MayOur paper got the UCSC Deans' Undergraduate Research Award. [Link]
AprilI'm starting a research internship at Embry–Riddle Aeronautical University this summer.