4 papers
When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary
Artem Trofimov, Boris Novikov
AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial…
In-IDE Toolkit for Developers of AI-Based Features
Yaroslav Sokolov, Yury Khudyakov, Lenar Sharipov +3
AI-enabled features built on LLMs and agentic workflows are difficult to test, debug, and reproduce, especially for product-focused software engineers without a machine learning ba…
VegaChat: A Robust Framework for LLM-Based Chart Generation and Assessment
Marko Hostnik, Rauf Kurbanov, Yaroslav Sokolov +1
Natural-language-to-visualization (NL2VIS) systems based on large language models (LLMs) have substantially improved the accessibility of data visualization. However, their further…
JetTrain: IDE-Native Machine Learning Experiments
Artem Trofimov, Mikhail Kostyukov, Sergei Ugdyzhekov +3
Integrated development environments (IDEs) are prevalent code-writing and debugging tools. However, they have yet to be widely adopted for launching machine learning (ML) experimen…