4 papers
Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment
Kirill Vasilevski, Ximing Dong, Benjamin Rombaut +8
LLMs have substantially improved software engineering yet real-world development requires architectural understanding. Such understanding is prohibitively expensive to label manual…
SynConfRoute: Syntax-Aware Routing for Efficient Code Completion with Small CodeLLMs
Kishanthan Thangarajah, Boyuan Chen, Ahmed E. Hassan
Enterprises want AI code completion that is both high-quality and private, but they face a tension: proprietary models yield better results yet risk exposing proprietary code, whil…
Detecting Protracted Vulnerabilities in Open Source Projects
Arjun Sridharkumar, Sara Al Hajj Ibrahim, Jiayuan Zhou +4
Timely resolution and disclosure of vulnerabilities are essential for maintaining the security of open-source software. However, many vulnerabilities remain unreported, unpatched,…
Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents
Benjamin Rombaut, Sogol Masoumzadeh, Kirill Vasilevski +2
Large language models (LLMs) are increasingly integrated into autonomous systems, giving rise to a new class of software known as Agentware, where LLM-powered agents perform comple…