collaborators

9 papers

cs.AI2026

AST-PAC: AST-guided Membership Inference for Code

Roham Koohestani, Ali Al-Kaswan, Jonathan Katzy +1

Code Large Language Models are frequently trained on massive datasets containing restrictively licensed source code. This creates urgent data governance and copyright challenges. M…

cs.AI2026

TriCEGAR: A Trace-Driven Abstraction Mechanism for Agentic AI

Roham Koohestani, Ateş Görpelioğlu, Egor Klimov +2

Agentic AI systems act through tools and evolve their behavior over long, stochastic interaction traces. This setting complicates assurance, because behavior depends on nondetermin…

cs.AI2026

Are Agents Probabilistic Automata? A Trace-Based, Memory-Constrained Theory of Agentic AI

Roham Koohestani, Ziyou Li, Anton Podkopaev +1

This paper studies standard controller architectures for agentic AI and derives automata-theoretic models of their interaction behavior via trace semantics and abstraction. We mode…

cs.SE2025

Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality

Roham Koohestani, Philippe de Bekker, Begüm Koç +1

Benchmarks are essential for unified evaluation and reproducibility. The rapid rise of Artificial Intelligence for Software Engineering (AI4SE) has produced numerous benchmarks for…

cs.SE2025

Does In-IDE Calibration of Large Language Models work at Scale?

Roham Koohestani, Agnia Sergeyuk, David Gros +4

The introduction of large language models into integrated development environments (IDEs) is revolutionizing software engineering, yet it poses challenges to the usefulness and rel…

cs.SE2025

Code4MeV2: a Research-oriented Code-completion Platform

Roham Koohestani, Parham Bateni, Aydin Ebrahimi +3

The adoption of AI-powered code completion tools in software development has increased substantially, yet the user interaction data produced by these systems remain proprietary wit…