I am a third year PhD student at the Machine Learning Department at Carnegie Mellon University. I am interested in the following questions:
how do we make AI systems better at reasoning
how can we enable continual learning in the era of modern Deep Learning
I am fortunate to be advised by Andrea Zanette.
Previously, I worked as a Research Fellow at Microsoft Research India, where I worked on Retrieval and Software Agents with Nagarajan Natarajan.
Before that, I spent my undergrad at IIT Delhi where I worked on Generalized Planning with Mausam and Parag Singla.
news
August 2024
started my PhD at CMU
August 2023
started working at Microsoft Research India as a Research Fellow
July 2023
completed B.Tech and M.Tech from IIT Delhi
selected publications
(* denotes equal contribution)
Training Language Models to Fail Gracefully Daman Arora, Xuecheng Liu, Himanshu Gaurav Singh, Fahim Tajwar, Abitha Thankaraj, Ruslan Salakhutdinov, Haiwen Feng, Yuda Song, Andrea Zanette arXiv preprint, 2026 paper
Message Passing Enables Efficient Reasoning
Xuecheng Liu*, Daman Arora*, Gokul Swamy, Andrea Zanette Conference on Language Modeling (COLM), 2026Outstanding Paper paper
Maximum Likelihood Reinforcement Learning
Fahim Tajwar*, Guanning Zeng*, Yueer Zhou, Yuda Song, Daman Arora, Yiding Jiang, Jeff Schneider, Ruslan Salakhutdinov, Haiwen Feng, Andrea Zanette International Conference on Machine Learning (ICML), 2026Oral paper
| project
| code
Training Language Models to Reason Efficiently Daman Arora, Andrea Zanette Neural Information Processing Systems, 2025 paper
| blog
| code
| cite
Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models Daman Arora*, Himanshu Gaurav Singh*, Mausam Empirical Methods in Natural Language Processing (EMNLP), 2023 paper
| code
| cite
MASAI: Modular Architecture for Software-engineering AI Agents Daman Arora*, Atharv Sonwane*, Nalin Wadhwa*, Abhav Mehrotra, Saiteja Utpala, Ramakrishna B Bairi, Aditya Kanade, Nagarajan Natarajan NeurIPS Workshop on Open-World Agents: Synergizing Reasoning and Decision-Making in Open-World Environments (OWA-2024) paper
| blog
| cite
