I am a PhD student at UC Berkeley in the Programming Systems group and the Sky Lab advised by Koushik Sen. I broadly research techniques at the intersection of Programming Languages, Software Engineering, and AI.

I work on software reliability in the age of large-language models (LLMs). I approach this from two angles: (1) building evaluation platforms and (2) introducing guardrails like search and assertions. A key piece of this is breathing life into static codebases, enabling program analysis and training better LLMs with execution awareness.

Previously, I worked at Microsoft Research (MSR) in the Programming Languages and Systems Group on developer and debugging tools for cloud reliability.

If you’d like to collaborate, drop me an email at: manishs@berkeley.edu

News

Apr 2024. 🏆 Honored to have received the Tong Leong Lim Pre-Doctoral Prize at UC Berkeley
Mar 2024. 🏆 Honored to have received the 2024 Outstanding Graduate Student Instructor Award at UC Berkeley
Jan 2024. Interning (returning) with the Systems Innovation group at Microsoft Research in Summer'24! Exploring next-generation AI Assisted System Reliability.
Sept 2023. ✔︎ Passed the Programming Languages Preliminary Exam at UC Berkeley!
May 2023. Taught my first class: CS164: Compilers and Programming Languages at UC Berkeley!
Nov 2022. 🏆 Our empirical study @ Microsoft Research on production incidents in large-scale cloud services received the Best Paper Award 🏆 at SoCC 2022.
Aug 2022. Started my Ph.D. at UC Berkeley advised by Prof. Koushik Sen. Joining the Sky Lab and the Programming Systems group!

Publications

R2E: Turning any GitHub Repository into a Programming Agent Environment
Manish Shetty*, Naman Jain*, Tianjun Zhang, King Han, Koushik Sen, Ion Stoica
ICML 2024: Proceedings of the 41st International Conference on Machine Learning
ICLR 2024 @ LLMAgents Workshop

paper / code / website

Building AI Agents for Autonomous Clouds: Challenges and Design Principles
Manish Shetty, Yinfang Chen, Gagan Somashekar, Minghua Ma, Yogesh Simmhan, Xuchao Zhang, Jonathan Mace, Dax Vandevoorde, Pedro Las-Casas, Shachee Mishra Gupta, Suman Nath, Chetan Bansal, Saravan Rajmohan
SoCC 2024: To appear at the 14th Symposium on Cloud Computing

paper / featured on Microsoft Research Blog

LM Assertions: Computational Constraints for Self-Refining LM Pipelines
Arnav Singhvi*, Manish Shetty*, Shangyin Tan*, Chris Potts, Koushik Sen, Matei Zaharia, Omar Khattab
Preprint, 2024 (Under Submission)

paper / code / tweet-1 / tweet-2 / blog

CodeScholar: Growing Idiomatic Code Examples
Manish Shetty, Koushik Sen, Ion Stoica
Tech Report, 2023

paper / code

How to Fight Production Incidents? An Empirical Study on a Large-scale Cloud Service
Supriyo Ghosh, Manish Shetty, Chetan Bansal, Suman Nath
SoCC 2022: Proceedings of the 13th Symposium on Cloud Computing

paper / Best Paper Award 🏆

AutoTSG: Learning and Synthesis for Incident Troubleshooting
Manish Shetty, Chetan Bansal, Sai Upadhyayula, Arjun Radhakrishna, Anurag Gupta
FSE 2022: Proceedings of the 30th ACM Symposium on the Foundations of Software Engineering

paper

DeepAnalyze: Learning to Localize Crashes at Scale
Manish Shetty, Chetan Bansal, Suman Nath, Sean Bowles, Henry Wang, Ozgur Arman, Siamak Ahari
ICSE 2022: Proceedings of the 44th International Conference on Software Engineering

paper / slides / talk-1 / talk-2 / talk-3

Neural Knowledge Extraction From Cloud Service Incidents
Manish Shetty, Chetan Bansal, Sumit Kumar, Nikitha Rao, Nachiappan Nagappan, Thomas Zimmermann
ICSE 2021: Proceedings of the 43rd International Conference on Software Engineering

paper / slides / talk / featured on VentureBeat

Awards

Teaching

UC Berkeley:

Service

Projects

r2e
$ Turn any GitHub repo into a dynamic environment for programming agents.
codescholar
$ Growing programs graphs idiomatically for API usage examples.
pat, yappy, & sast
$ A new suite of program analysis tools for Python over AST, CFG, and PDGs.