Shuyin Ouyang

Yanzheng Xiang, Hanqi Yan, Shuyin Ouyang et al.

This study evaluates large language models (LLMs) in generating code from algorithm descriptions in recent NLP papers. The task requires two key competencies: (1) algorithm comprehension: synthesizing information from papers and academic literature to understand implementation logic, and (2) coding expertise: identifying dependencies and correctly implementing necessary APIs. To facilitate rigorous evaluation, we introduce SciReplicate-Bench, a benchmark of 100 tasks from 36 NLP papers published in 2024, featuring detailed annotations and comprehensive test cases. Building on SciReplicate-Bench, we propose Sci-Reproducer, a dual-agent framework consisting of a Paper Agent that interprets algorithmic concepts from literature and a Code Agent that retrieves dependencies from repositories and implements solutions. To assess algorithm understanding, we introduce reasoning graph accuracy, which quantifies similarity between generated and reference reasoning graphs derived from code comments and structure. For evaluating implementation quality, we employ execution accuracy, CodeBLEU, and repository dependency/API recall metrics. In our experiments, we evaluate various powerful non-reasoning and reasoning LLMs as foundational models. The best-performing LLM using \ModelName~achieves only 39% execution accuracy, highlighting the benchmark's difficulty. Our analysis identifies missing or inconsistent algorithm descriptions as key barriers to successful reproduction. We make available our benchmark and code at https://github.com/xyzCS/SciReplicate-Bench and project homepage at https://xyzcs.github.io/scireplicate.github.io/.

Yihang Zhao, Bohui Zhang, Xi Hu et al.

Past ontology requirements engineering (ORE) has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts, especially in large projects. Current OntoChat offers a framework for ORE that utilises large language models (LLMs) to streamline the process through four key functions: user story creation, competency question (CQ) extraction, CQ filtration and analysis, and ontology testing support. In OntoChat, users are expected to prompt the chatbot to generate user stories. However, preliminary evaluations revealed that they struggle to do this effectively. To address this issue, we experimented with a research method called participatory prompting, which involves researcher-mediated interactions to help users without deep knowledge of LLMs use the chatbot more effectively. This participatory prompting user study produces pre-defined prompt templates based on user queries, focusing on creating and refining personas, goals, scenarios, sample data, and data resources for user stories. These refined user stories will subsequently be converted into CQs.

Shuyin Ouyang, Zhaozhi Qian, Faroq AL-Tam et al.

Reinforcement Learning (RL) is an important paradigm for aligning Diffusion Language Models (DLMs) toward functional correctness in code generation. However, these models often encounter a ``capability cliff'' on complex tasks, where execution-based semantic rewards become too low to provide a viable learning signal. In this paper, we present a systematic empirical study of RL post-training for diffusion-based code generation along three axes: reward design, hint-conditioned sampling, and task difficulty. We investigate the effectiveness of execution-free rewards as alternatives to traditional unit-test execution, the role of training-time hint-conditioned diffusion sampling in mitigating exploration bottlenecks, and the impact of these design choices varies across tasks with different difficulty levels. Across HumanEval, MBPP, and LiveCodeBench, we find that static checking is the strongest overall standalone execution-free reward in our setting, especially improving DiffuCoder from 53.9 to 67.1 on HumanEval and from 14.9 to 15.5 on LiveCodeBench while reducing rollout time by 9.4\%. We further find that moderate AST-based hinting is most useful on harder benchmarks, while the best reward design depends strongly on task difficulty: similarity-based rewards are more effective on easier subsets, whereas static checking is more reliable on harder subsets where execution rewards are low. These findings suggest that reward design and training guidance substantially affect diffusion RL performance in our evaluated code-generation setting.

Shuyin Ouyang, Jie M. Zhang, Jingzhi Gong et al.

Software architecture diagrams are important design artifacts for communicating system structure, behavior, and data organization throughout the software development lifecycle. Although recent progress in large language models has substantially advanced code-centric software engineering tasks such as code generation, testing, and maintenance, the ability of modern vision-language models (VLMs) to understand software architecture diagrams remains underexplored. To address this gap, we present SADU, a benchmark for Software Architecture Diagram Understanding that evaluates VLMs on architecture diagrams as structured software engineering artifacts rather than generic images. SADU contains 154 carefully curated diagrams spanning behavioral, structural, and ER diagrams, paired with structured annotations and 2,431 question-answer tasks covering counting and retrieval reasoning. We evaluate 11 state-of-the-art VLMs from the Gemini, Claude, GPT, and Qwen families. Our results show that software architecture diagram understanding remains challenging for current models: the best-performing model gemini-3-flash-preview achieves only 70.18\% accuracy, while gpt-4o-mini only achieves 17.77\% accuracy. The results further reveal the weaknesses in diagram reasoning and visual relation grounding, highlighting a gap between current VLMs and the needs of design-stage software engineering. SADU provides a foundation for future research on diagram-aware AI systems and more faithful AI-assisted software engineering workflows.