arXiv subjects

Oleksandr Zaitsev

Publications and source records attributed to Oleksandr Zaitsev.

4 recordsLinked to original sources

arXiv2026

Evaluating Package-Level Scoping Strategies for Repository-Level Code Completion in Pharo

Source code is organized in repositories, packages, and projects, yet token-level completion engines rarely exploit this structure. Pharo provides a semantic completion engine based on ordered, lazy heuristics that retrieve and rank candidates. Its default strategy follows language semantics and scoping rules, but ignores package structure and dependencies. Consequently, classes from the same package or project, and classes used by them, receive no special priority. We introduce and evaluate three package-aware heuristics: Lateral Packages, Direct Package Dependencies, and Two-Level Package Dependencies. Our benchmark covers method call sites from 219 packages, including 4,535 classes and 35,972 methods across major Pharo projects such as Iceberg, Moose, Roassal, Seaside, and Spec. We assess class-name and method-name completion and ask whether explicit package dependencies can provide a lightweight structural signal for improving candidate ranking without introducing a new learning model. The Direct Package Dependencies heuristic produced the strongest results. For 3-character prefixes, Mean Reciprocal Rank increased from 0.20 to 0.44 for class-name completion and from 0.10 to 0.41 for method-name completion. These findings show that package-aware strategies provide more accurate and relevant suggestions than the default Semantics-Based strategy on the evaluated projects. Based on the improvement in class-name completion, the Pharo Industrial Consortium adopted the Direct Package Dependencies heuristic for Pharo 13.

cs.SE↗

arXiv2026

Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo

Large Language Models (LLMs) unlocked new possibilities in automated code writing, becoming the backbone of most code completion tools. While LLMs excel in mainstream languages, they often lack support for the so-called low-resource languages where training data is scarce. As a result, these languages lag behind in the quality of code completion tooling available to their communities. A concrete example is Pharo, a Smalltalk-inspired language whose IDE currently offers only single-token completion. In this work, we report on our experience bringing LLM-based code completion to Pharo. First, we describe an end-to-end pipeline that combines Pharo-specific data curation, continued pre-training and fine-tuning of open code LLMs. Second, we introduce a set of Pharo code completion benchmarks designed to evaluate whether models (i) learn Pharo's syntax and (ii) accurately complete masked Pharo code from real-world GitHub repositories. Third, we show empirically that Pharo-specialized models substantially outperform their original base checkpoints and also exceed the accuracy of substantially larger code LLMs on Pharo completion. Overall, our case study demonstrates the feasibility of bringing strong LLM-based code completion to low-resource programming languages, with models small enough to provide ``real-time'' in-IDE support.

cs.SE↗

arXiv2026

Package-Aware Approach for Repository-Level Code Completion in Pharo

Pharo offers a sophisticated completion engine based on semantic heuristics, which coordinates specific fetchers within a lazy architecture. These heuristics can be recomposed to support various activities (e.g., live programming or history usage navigation). While this system is powerful, it does not account for the repository structure when suggesting global names such as class names, class variables, or global variables. As a result, it does not prioritize classes within the same package or project, treating all global names equally. In this paper, we present a new heuristic that addresses this limitation. Our approach searches variable names in a structured manner: it begins with the package of the requesting class, then expands to other packages within the same repository, and finally considers the global namespace. We describe the logic behind this heuristic and evaluate it against the default semantic heuristic and one that directly queries the global namespace. Preliminary results indicate that the Mean Reciprocal Rank (MRR) improves, confirming that package-awareness completions deliver more accurate and relevant suggestions than the previous flat global approach.

cs.SE↗

arXiv2023

Cormas: The Software for Participatory Modelling and its Application for Managing Natural Resources in Senegal

Cormas is an agent-based simulation platform developed in the late 90s by the Green research at CIRAD unit to support the management of natural resources and understand the interactions between natural and social dynamics. This platform is well-suited for a participatory simulation approach that empowers local stakeholders by including them in all modelling and knowledge-sharing steps. In this short paper, we present the Cormas platform and discuss its unique features and their importance for the participatory simulation approach. We then present the early results of our ongoing study on managing pastoral resources in the Sahel region, identify the problems faced by local stakeholders, and discuss the potential use of Cormas at the next stage of our study to collectively model and understand the effective ways of managing the shared agro-sylvo-pastoral resources.

cs.MA↗