Publications

Roham Koohestani, Agnia Sergeyuk, David Gros, Claudio Spiess, Sergey Titov, Prem Devanbu, Maliheh Izadi (2025). Does In-IDE Calibration of Large Language Models Work at Scale?. arXiv preprint arXiv:2510.22614.

Roham Koohestani, Parham Bateni, Aydin Ebrahimi, Behdad Etezadi, Kiarash Karimi, Maliheh Izadi (2025). Code4MeV2: A Research-oriented Code-completion Platform. arXiv preprint arXiv:2510.03755.

Roham Koohestani, Ziyou Li, Anton Podkopaev, Maliheh Izadi (2025). Are Agents Just Automata? On the Formal Equivalence Between Agentic AI and the Chomsky Hierarchy. arXiv preprint arXiv:2510.23487.

Roham Koohestani (2025). AgentGuard: Runtime Verification of AI Agents. arXiv preprint arXiv:2509.23864.

Roham Koohestani, Philippe De Bekker, Maliheh Izadi (2025). Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol. arXiv preprint arXiv:2503.05860.

Roham Koohestani, Maliheh Izadi (2025). Rethinking IDE Customization for Enhanced HAX: A Hyperdimensional Perspective. IDE 2025 Workshop.

Anastasiia Birillo, Ilya Vlasov, Roham Koohestani, Maliheh Izadi, Konstantin Grotov, Dmitry Botov, Mauricio Verano Merino, Niels Kok, Markus Borg (2025). IDE 2025. IDE 2025.

Roham Koohestani, Maliheh Izadi (2025). HyperSeq: A Hyper-Adaptive Representation for Predictive Sequencing of States. FSE 2025.

Amirhossein Deljouyi, Roham Koohestani, Maliheh Izadi, Andy Zaidman (2024). Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests. arXiv preprint arXiv:2408.11710.