2 citations · 3 across the 12 of their papers we have counts for
13 papers
SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation
Sijia Gu, Noor Nashid, Ali Mesbah
While autonomous coding agents have significantly advanced automated test generation, they remain fundamentally limited by lazy generation, a phenomenon where agents prematurely te…
Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair
Noor Nashid, Daniel Ding, Keheliya Gallaba +2
Automated program repair has traditionally focused on single-hunk defects, overlooking multi-hunk bugs that are prevalent in real-world systems. Repairing these bugs requires coord…
VISCA: Inferring Component Abstractions for Automated End-to-End Testing
Parsa Alian, Martin Tang, Ali Mesbah
Providing optimal contextual input presents a significant challenge for automated end-to-end (E2E) test generation using large language models (LLMs), a limitation that current app…
Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges
Noor Nashid, Daniel Ding, Keheliya Gallaba +2
Multi-hunk bugs, where fixes span disjoint regions of code, are common in practice, yet remain underrepresented in automated repair. Existing techniques and benchmarks pre-dominant…
Issue2Test: Generating Reproducing Test Cases from Issue Reports
Noor Nashid, Islem Bouzenia, Michael Pradel +1
Automated tools for solving GitHub issues are receiving significant attention by both researchers and practitioners, e.g., in the form of foundation models and LLM-based agents pro…
LLM Test Generation via Iterative Hybrid Program Analysis
Sijia Gu, Noor Nashid, Ali Mesbah
Automating unit test generation remains a significant challenge, particularly for complex methods in real-world projects. While Large Language Models (LLMs) have made strides in co…
NaviQAte: Functionality-Guided Web Application Navigation
Mobina Shahbandeh, Parsa Alian, Noor Nashid +1
End-to-end web testing is challenging due to the need to explore diverse web application functionalities. Current state-of-the-art methods, such as WebCanvas, are not designed for…
Scalable Similarity-Aware Test Suite Minimization with Reinforcement Learning
Sijia Gu, Ali Mesbah
The Multi-Criteria Test Suite Minimization (MCTSM) problem aims to remove redundant test cases, guided by adequacy criteria such as code coverage or fault detection capability. How…
Dockerfile Flakiness: Characterization and Repair
Taha Shabani, Noor Nashid, Parsa Alian +1
Dockerfile flakiness-unpredictable temporal build failures caused by external dependencies and evolving environments-undermines deployment reliability and increases debugging overh…
Feature-Driven End-To-End Test Generation
Parsa Alian, Noor Nashid, Mobina Shahbandeh +2
End-to-end (E2E) testing is essential for ensuring web application quality. However, manual test creation is time-consuming, and current test generation techniques produce incohere…
Contextual API Completion for Unseen Repositories Using LLMs
Noor Nashid, Taha Shabani, Parsa Alian +1
Large language models have made substantial progress in addressing diverse code-related tasks. However, their adoption is hindered by inconsistencies in generating output due to th…
Fine-Grained Assertion-Based Test Selection
Sijia Gu, Ali Mesbah
For large software applications, running the whole test suite after each code change is time- and resource-intensive. Regression test selection techniques aim at reducing test exec…
Semantic Constraint Inference for Web Form Test Generation
Parsa Alian, Noor Nashid, Mobina Shahbandeh +1
Automated test generation for web forms has been a longstanding challenge, exacerbated by the intrinsic human-centric design of forms and their complex, device-agnostic structures.…