6 papers
Grounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test Generation
Michele Tufano, James McClure, José Cambronero +7
LLM-based agents are increasingly used for coding tasks, where they have outperformed many classical approaches and scaled to repository-level tasks, such as test generation. Howev…
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…
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…
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…
Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
Runxiang Cheng, Michele Tufano, José Cambronero +7
Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily for validating fixes and aiding fix generation. In practice, when developers…
Towards a Human-in-the-Loop Framework for Reliable Patch Evaluation Using an LLM-as-a-Judge
Sherry Shi, Renyao Wei, Michele Tufano +4
Reliable evaluation is crucial for advancing Automated Program Repair (APR), but prevailing benchmarks rely on execution-based evaluation methods (unit test pass@k), which fail to…