215 citations · 354 across the 16 of their papers we have counts for
18 papers
From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale
Chandra Maddila, Mashrur Rashik, Euna Mehnaz Khan +4
AI coding agents are generating code at volumes that exceed the capacity of traditional peer review. At the same time, existing AI code review tools over-index on low-value suggest…
REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage
Smriti Jha, Matteo Paltenghi, Chandra Maddila +3
Production deployment of AI coding agents requires fast, reproducible evaluation signals. Existing industrial practices trade off speed and fidelity: online A/B testing takes weeks…
Wink: Recovering from Misbehaviors in Coding Agents
Rahul Nanda, Chandra Maddila, Smriti Jha +3
Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these age…
Agentic Program Repair from Test Failures at Scale: A Neuro-symbolic approach with static analysis and test execution feedback
Chandra Maddila, Adam Tait, Claire Chang +21
Aim: With the advent of LLMs, sophisticated agentic program repair has become viable at large organizations with large codebases. In this work, we develop an Engineering Agent that…
AI-Assisted Fixes to Code Review Comments at Scale
Chandra Maddila, Negar Ghorbani, James Saindon +7
Aim. There are 10s of thousands of code review comments each week at Meta. We developed Metamate for Code Review (MetaMateCR) that provides AI-assisted fixes for reviewer comments…
Moving Faster and Reducing Risk: Using LLMs in Release Deployment
Rui Abreu, Vijayaraghavan Murali, Peter C Rigby +7
Release engineering has traditionally focused on continuously delivering features and bug fixes to users, but at a certain scale, it becomes impossible for a release engineering te…
AI-Assisted SQL Authoring at Industry Scale
Chandra Maddila, Negar Ghorbani, Kosay Jabre +8
SqlCompose brings generative AI into the data analytics domain. SQL is declarative, has formal table schemas, and is often written in a non-linear manner. We address each of these…
Multi-line AI-assisted Code Authoring
Omer Dunay, Daniel Cheng, Adam Tait +9
CodeCompose is an AI-assisted code authoring tool powered by large language models (LLMs) that provides inline suggestions to 10's of thousands of developers at Meta. In this paper…
Improving Code Reviewer Recommendation: Accuracy, Latency, Workload, and Bystanders
Peter C. Rigby, Seth Rogers, Sadruddin Saleem +5
The code review team at Meta is continuously improving the code review process. To evaluate the new recommenders, we conduct three A/B tests which are a type of randomized controll…
AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation
Vijayaraghavan Murali, Chandra Maddila, Imad Ahmad +6
Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we pres…
Using Large-scale Heterogeneous Graph Representation Learning for Code Review Recommendations at Microsoft
Jiyang Zhang, Chandra Maddila, Ram Bairi +6
Code review is an integral part of any mature software development process, and identifying the best reviewer for a code change is a well-accepted problem within the software engin…
What are Weak Links in the npm Supply Chain?
Nusrat Zahan, Thomas Zimmermann, Patrice Godefroid +3
Modern software development frequently uses third-party packages, raising the concern of supply chain security attacks. Many attackers target popular package managers, like npm, an…
Nalanda: A Socio-Technical Graph for Building Software Analytics Tools at Enterprise Scale
Chandra Maddila, Suhas Shanbhogue, Apoorva Agrawal +6
Software development is information-dense knowledge work that requires collaboration with other developers and awareness of artifacts such as work items, pull requests, and files.…
ConE: A Concurrent Edit Detection Tool for Large Scale Software Development
Chandra Maddila, Nachiappan Nagappan, Christian Bird +2
Modern, complex software systems are being continuously extended and adjusted. The developers responsible for this may come from different teams or organizations, and may be distri…
Nudge: Accelerating Overdue Pull Requests Towards Completion
Chandra Maddila, Sai Surya Upadrasta, Chetan Bansal +3
Pull requests are a key part of the collaborative software development and code review process today. However, pull requests can also slow down the software development process whe…
A Tale of Two Cities: Software Developers Working from Home During the COVID-19 Pandemic
Denae Ford, Margaret-Anne Storey, Thomas Zimmermann +6
The COVID-19 pandemic has shaken the world to its core and has provoked an overnight exodus of developers that normally worked in an office setting to working from home. The magnit…
Studying Ransomware Attacks Using Web Search Logs
Chetan Bansal, Pantazis Deligiannis, Chandra Maddila +1
Cyber attacks are increasingly becoming prevalent and causing significant damage to individuals, businesses and even countries. In particular, ransomware attacks have grown signifi…
Product Insights: Analyzing Product Intents in Web Search
Nikitha Rao, Chetan Bansal, Subhabrata Mukherjee +1
Web search engines are frequently used to access information about products. This has increased in recent times with the rising popularity of e-commerce. However, there is limited…