8 papers
TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
Alex Mathai, Shobini Iyer, Aleksandr Nogikh +4
Coding agents are increasingly used to accelerate code generation in many downstream tasks, such as fixing bugs, building applications, and prototyping. However, despite their valu…
Customizing an LLM for Enterprise Software Engineering
Aditya Kini, Satish Chandra, Milad Hashemi +15
Enterprise software development is a continuous evolutionary process, characterized by incremental additions, architectural revisions, production deployments and rigorous maintenan…
Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All
Chenxi Huang, Alex Mathai, Feiyang Yu +7
Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Lan…
RubberDuckBench: A Benchmark for AI Coding Assistants
Ferida Mohammed, Fatma Ayad, Petros Maniatis +2
Programmers are turning to AI coding assistants to answer questions about their code. Benchmarks are needed to soundly evaluate these systems and understand their performance. To e…
kAgent: An execution-guided crash resolution agent for the Linux kernel
Alex Mathai, Chenxi Huang, Suwei Ma +7
Fuzzing frameworks like syzkaller have uncovered thousands of Linux kernel crashes, many of which are critical and security-sensitive. However, the ability to rapidly repair these…
CRQBench: A Benchmark of Code Reasoning Questions
Elizabeth Dinella, Satish Chandra, Petros Maniatis
Large Language Models have demonstrated exceptional proficiency on coding tasks, but it is challenging to precisely evaluate their code reasoning ability. Existing benchmarks are i…