activity
20242026
collaborators
Showing cs.SEShow all

6 papers · 1 filter

cs.SE2026

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…

cs.SE2026

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…

cs.SE2026

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…

cs.SE2025

EditLord: Learning Code Transformation Rules for Code Editing

Weichen Li, Albert Jan, Baishakhi Ray +3

Code editing is a foundational task in software development, where its effectiveness depends on whether it introduces desired code property changes without changing the original co…

cs.SE2025

CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation

Jinjun Peng, Leyi Cui, Kele Huang +2

Large Language Models (LLMs) have significantly aided developers by generating or assisting in code writing, enhancing productivity across various tasks. While identifying incorrec…

cs.SE2024

KGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution

Alex Mathai, Chenxi Huang, Petros Maniatis +4

Large Language Models (LLMs) are consistently improving at increasingly realistic software engineering (SE) tasks. In real-world software stacks, significant SE effort is spent dev…