29 citations · 32 across the 8 of their papers we have counts for
9 papers
Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction
Mohsen EsfandyariDoulabi, Lawrence Arkoh, Biruk Tadesse +4
Predicting whether an LLM agent will fail has emerged as a promising direction for supporting intervention during execution. Recent approaches report strong predictive performance,…
An Empirical Analysis of Cross-OS Portability Issues in Python Projects
Denini Silva, MohamadAli Farahat, Marcelo d'Amorim
While Python is designed as a cross-platform language, real-world applications encounter portability failures when deployed across different operating systems. We present the first…
Code Quality Analysis of Translations from C to Rust
Biruk Tadesse, Vikram Nitin, Mazin Salah +3
C/C++ is a prevalent programming language. Yet, it suffers from significant memory and thread-safety issues. Recent studies have explored automated translation of C/C++ to safer la…
SmartOracle -- An Agentic Approach to Mitigate Noise in Differential Oracles
Srinath Srinivasan, Tim Menzies, Marcelo D'Amorim
Differential fuzzers detect bugs by executing identical inputs across distinct implementations of the same specification, such as JavaScript interpreters. Validating the outputs re…
Agentic LMs: Hunting Down Test Smells
Rian Melo, Pedro Simões, Rohit Gheyi +5
Test smells reduce test suite reliability and complicate maintenance. While many methods detect test smells, few support automated removal, and most rely on static analysis or mach…
A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback
Ummay Kulsum, Haotian Zhu, Bowen Xu +1
Recent work in automated program repair (APR) proposes the use of reasoning and patch validation feedback to reduce the semantic gap between the LLMs and the code under analysis. T…
Test Oracle Automation in the era of LLMs
Facundo Molina, Alessandra Gorla
The effectiveness of a test suite in detecting faults highly depends on the correctness and completeness of its test oracles. Large Language Models (LLMs) have already demonstrated…
Just another copy and paste? Comparing the security vulnerabilities of ChatGPT generated code and StackOverflow answers
Sivana Hamer, Marcelo d'Amorim, Laurie Williams
Sonatype's 2023 report found that 97% of developers and security leads integrate generative Artificial Intelligence (AI), particularly Large Language Models (LLMs), into their deve…
NCQ: Code reuse support for node.js developers
Brittany Reid, Marcelo d`Amorim, Markus Wagner +1
Code reuse is an important part of software development. The adoption of code reuse practices is especially common among Node.js developers. The Node.js package manager, NPM, index…