Shashank Kirtania
Incoming CS PhD at University of Michigan
shashankkirtania123 [AT] gmail.com
Bio
Hi! I am an incoming PhD student at the University of Michigan.
Previously, I was a Research Fellow (Pre-Doctoral) at Microsoft Research India, where I was part of the program synthesis group (PROSE) and the AI4Code team in Bengaluru. I worked on AI for Code and AI for Math, with the goal of making automated programming more trustworthy by developing AI systems that generate robust, correct, and verifiable code—leveraging techniques from Formal Methods, Software Engineering, and Artificial Intelligence to ensure the reliability and correctness of automatically generated programs.
I was privileged to work with Aditya Kanade, Ashish Tiwari, Gustavo Soares, Arjun Radhakrishna, Sumit Gulwani, and Arun Iyer.
For fun, I enjoy playing tennis, running and occasional bouldering.
Publications
Most recent publications on Google Scholar.
‡ indicates equal contribution.
Activation Steering in Theorem Prover LLMs
Shashank Kirtania, Arun Iyer
FM in Wild Workshop ICLR'25, Under Submission at ICLR 2026
STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with Feedback
Shashank Kirtania‡, Naman Gupta‡, Priyanshu Gupta, Krishna Kariya, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares
Empirical Methods in Natural Language Processing 2025, DL for Code Workshop NeurIPS 2025
Improving Language Agents with BREW:
Shashank Kirtania, Param Biyani, Priyanshu Gupta, Yasharth Bajpai, Roshni Iyer, Sumit Gulwani, Gustavo Soares
Multi-Turn Interaction Workshop at NeurIPS 2025, Under Submission at ICLR 2026
MetaReflection: Learning Instructions for Language Agents using Past Reflections
Shashank Kirtania‡, Priyanshu Gupta‡, Annanya Singha‡, Sumit Gulwani, Arjun Radhakrishna, Sherry Shi, Gustavo Soares
Empirical Methods in Natural Language Processing 2024
LOGIC-LM++: Multi-Step Refinement for Symbolic Formulations
Shashank Kirtania, Priyanshu Gupta, Arjun Radhakrishna
Workshop on Natural Language Reasoning at ACL 2024
Activation Steering in Theorem Prover LLMs
Shashank Kirtania, Arun Iyer
FM in Wild Workshop ICLR'25, Under Submission at ICLR 2026
STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with Feedback
Shashank Kirtania‡, Naman Gupta‡, Priyanshu Gupta, Krishna Kariya, Sumit Gulwani, Arun Iyer, Suresh Parthasarathy, Arjun Radhakrishna, Sriram K. Rajamani, Gustavo Soares
Empirical Methods in Natural Language Processing 2025, DL for Code Workshop NeurIPS 2025
Improving Language Agents with BREW:
Shashank Kirtania, Param Biyani, Priyanshu Gupta, Yasharth Bajpai, Roshni Iyer, Sumit Gulwani, Gustavo Soares
Multi-Turn Interaction Workshop at NeurIPS 2025, Under Submission at ICLR 2026
MetaReflection: Learning Instructions for Language Agents using Past Reflections
Shashank Kirtania‡, Priyanshu Gupta‡, Annanya Singha‡, Sumit Gulwani, Arjun Radhakrishna, Sherry Shi, Gustavo Soares
Empirical Methods in Natural Language Processing 2024
LOGIC-LM++: Multi-Step Refinement for Symbolic Formulations
Shashank Kirtania, Priyanshu Gupta, Arjun Radhakrishna
Workshop on Natural Language Reasoning at ACL 2024
DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documents
Tejasvee Bisen, Mohammed Javed, Shashank Kirtania, P Nagabhushan
Pattern Analysis and Applications, Springer, 2023.
Train of Thought
A collection of trains of thought and lines of research, inspired by Kartik Chandra and Shubhra Mishra.
Research Subway — open full size
CV
Full Resume in PDF.
-
Microsoft Research India 2023 - nowML Resident
AI4Code -
Wadhwani AI 2023 - 2023Research Engineer, Intern
-
Thapar Institue of Engineering and Technology 2019 - 2023CS Major