XREPOTEST is introduced, a multilingual repository-level benchmark for unit test generation spanning five underexplored languages: Rust, Go, Julia, PHP, and Ruby, and Invocation Rate is proposed to assess whether generated tests meaningfully exercise the intended functionality.
Abstract
Large language models (LLMs) have shown promise for automated unit test generation, but existing evaluations largely rely on standalone settings and a narrow set of programming languages, overestimating real-world readiness. We introduce XREPOTEST, a multilingual repository-level benchmark for unit test generation spanning five underexplored languages: Rust, Go, Julia, PHP, and Ruby. XREPOTEST evaluates tests under realistic repository constraints using a containerized execution framework and multiple context augmentation strategies, including file-level, LSP-based, and retrieval-based context. Beyond standard metrics such as test pass rate and coverage, we propose Invocation Rate (IR) to assess whether generated tests meaningfully exercise the intended functionality. Experiments with 14 state-of-the-art LLMs, including Claude 4.5, GPT-5.2, DeepSeek V4-Pro, and Qwen families, reveal a substantial gap between standalone and repository-level performance, as well as trade-offs between richer context and test reliability. Overall, XREPOTEST provides a challenging and informative benchmark to advance scalable and robust unit test generation in realistic software environments. The dataset and code are publicly available at: https://github.com/solis-team/XRepoTest
LLMs are increasingly used for code generation, yet they frequently hallucinate non-existent software packages, creating exploitable entry points into the software supply chain. We make four contributions to this problem. First, we show that prior evaluation methodologies systematically inflate hallucination rates by misclassifying standard-library modules as hallucinations in some languages. For Python, the overestimation reaches 9.4 percentage points. Second, we evaluate seven inference-time defenses for mitigating package hallucinations, including five guided decoding strategies (Greedy, Contrastive, DoLa, Nudging, and Active Layer-Contrastive Decoding), an iterative self-refinement approach (Self-Refine), and a Retrieval-Augmented Generation (RAG)-based defense.. Across eight models spanning five families and four programming languages (Python, JavaScript, Ruby, Rust), RAG reduces the package hallucination rate (PHR) in 18 of 32 model--language configurations. Third, we introduce Package Utility (PU) to assess whether defenses preserve valid and task-relevant recommendations. Among strategies evaluated, Greedy decoding provides the strongest average mitigation--utility trade-off. Fourth, we stress-test all strategies under adversarial prompts seeded with fabricated package names and find that PHR surges by up to 45 percentage points relative to standard prompts, with Ruby consistently the most vulnerable language (80.9--95.2\%). Under adversarial conditions, RAG and Self-Refine outperform all decoding-only strategies, indicating that robust defense requires either external grounding or iterative self-verification when prompts are actively hostile. Our results recast package hallucination as both a measurement problem and a decoding-time control problem, and they demonstrate that the choice of defense must be matched to the threat model and recommendation utility.
Albérick Euraste Djiré, Iyiola E. Olatunji, Melissa Tessa et al.· 1 citation
MAGE explains how externalized knowledge, bounded action, independent evaluation, and retained human authority can compose into a governed engineering environment, and proposes tests of when that environment turns commodity intelligence into durable engineering progress.
James C. Davis, Kelechi G. Kalu, Huiyun Peng et al.· 1 citation
An audit-and-placebo protocol is proposed that separates verifier artifacts, interaction scaffolding, and grounded feedback credit in evaluations of self-evolving test generators in evaluations of self-evolving test generators.
Yunhao Liang, Chengguang Gan, Ruixuan Ying et al.· 0 citations
This work explores the sputtering of additively manufactured (AM) materials for use in gridded ion source applications. The first part of the paper uses 316L stainless steel as an example to demonstrate that additively manufactured material does not exhibit adverse sputtering behavior, such as higher sputter yield, compared with conventionally manufactured material. To this end, three additively manufactured 316L stainless steel samples were exposed to the beam of a KDC-40 electrostatic gridded ion source at three distinct energy levels of 400, 600, and 800 eV on each side of the sample for a duration of one hour. The samples were masked to create a distinct boundary between treated and untreated regions, identifiable using profilometry, and were biased to -18V for testing. Samples were then examined using a Bruker optical profilometer and further processed using the open-source software Gwyddion to evaluate the sputtering yield. The sputter yield varied in the range 0.2-2 atoms/ion for 400-800 eV ions and increased with ion energy. The measured sputtering yield was fairly consistent with predictions from analytical models developed in prior literature, while exhibiting some variations potentially due to added effects of increased temperature and oxide layers. The second part of the paper demonstrates feasibility of using an additively manufactured tungsten-rhenium grids in existing KDC-40 electrostatic gridded ion source.
This prototype MRG image translocation software was helpful to 69% of patients with binocular diplopia, but limited by large angle strabismus because of the limited instrument field of view.
Edsel B Ing, Kevin Sha, Sarosh Dandoti et al.· Journal of neuro-ophthalmolo...· 0 citations
A diagnostic support system based on a unified web platform that classifies patients according to the risks of developing three diseases based on regularly collected clinical or audio data using classical supervised learning algorithms is presented.
Vedamurthy D R, Dr. Anup Ritti, A. Bibi et al.· International Journal for Re...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduAug 17, 2026
A USAF cadet and a Lincoln Laboratory researcher found AI chatbots can help nontechnical service members produce viable software applications for their unique problems.
