Tingting Bi

Juntao Chen, Tingting Bi, Yanlin Wang et al.

Modern software systems rely on dependency networks of reusable libraries, where breaking changes propagate and cause downstream consumers to fail. Despite growing research across ecosystems, no comprehensive synthesis exists. We conduct a systematic literature review of 97 primary studies, answering four research questions across five ecosystems: Maven/Java, npm/JavaScript, Python, Web APIs, and Linux distributions. The synthesis yields four results. First, a four-dimensional taxonomy along Nature, Detectability, Scope, and Visibility. Second, five reason categories and five impact dimensions, where maintenance and design improvements account for a larger share of breaking changes than new feature work. Third, 43 detection approaches that reach high accuracy on syntactic breaks but limited coverage on behavioral ones. Fourth, 66 strategies for communicating, preventing, and recovering from breaking changes, organized by the actor's role. Based on these findings, we identify three open challenges and three research opportunities. The challenges are behavioral break detection at scale, the failure of semantic versioning as a trust mechanism, and transitive dependency propagation under information asymmetry. The opportunities are LLM-augmented behavioral contract inference, ecosystem-level dependency graph intelligence, and domain-specific tooling for ML and data science.

Yanlin Wang, Xinyi Xu, Jiachi Chen et al.

The rise of large language models (LLMs) has sparked a surge of interest in agents, leading to the rapid growth of agent frameworks. Agent frameworks are software toolkits and libraries that provide standardized components, abstractions, and orchestration mechanisms to simplify agent development. Despite widespread use of agent frameworks, their practical applications and how they influence the agent development process remain underexplored. Different agent frameworks encounter similar problems during use, indicating that these recurring issues deserve greater attention and call for further improvements in agent framework design. Meanwhile, as the number of agent frameworks continues to grow and evolve, more than 80% of developers report difficulties in identifying the frameworks that best meet their specific development requirements. In this paper, we conduct the first empirical study of LLM-based agent frameworks, exploring real-world experiences of developers in building AI agents. To compare how well the agent frameworks meet developer needs, we further collect developer discussions for the ten previously identified agent frameworks, resulting in a total of 11,910 discussions. Finally, by analyzing these discussions, we compare the frameworks across five dimensions: development efficiency, functional abstraction, learning cost, performance optimization, and maintainability, which refers to how easily developers can update and extend both the framework itself and the agents built upon it over time. Our comparative analysis reveals significant differences among frameworks in how they meet the needs of agent developers. Overall, we provide a set of findings and implications for the LLM-driven AI agent framework ecosystem and offer insights for the design of future LLM-based agent frameworks and agent developers.

Zhiyuan Zou, Bangchao Wang, Peng Liang et al.

In the field of software traceability link recovery (TLR), textual similarity has long been regarded as the core criterion. However, in tasks involving natural language and programming language (NL-PL) artifacts, relying solely on textual similarity is limited by their semantic gap. To this end, we conducted a large-scale empirical evaluation across various types of TLR tasks, revealing the limitations of textual similarity in NL-PL scenarios. To address these limitations, we propose an approach that incorporates multiple domain-specific auxiliary strategies, identified through empirical analysis, into two models: the Heterogeneous Graph Transformer (HGT) via edge types and the prompt-based Gemini 2.5 Pro via additional input information. We then evaluated our approach using the widely studied requirements-to-code TLR task, a representative case of NL-PL TLR. Experimental results show that both the multi-strategy HGT and Gemini 2.5 Pro models outperformed their original counterparts without strategy integration. Furthermore, compared to the current state-of-the-art method HGNNLink, the multi-strategy HGT and Gemini 2.5 Pro models achieved average F1-score improvements of 3.68% and 8.84%, respectively, across twelve open-source projects, demonstrating the effectiveness of multi-strategy integration in enhancing overall model performance for the requirements-code TLR task.

Tingting Bi, Wei Ding, Peng Liang et al.

Architecture information is vital for Open Source Software (OSS) development, and mailing list is one of the widely used channels for developers to share and communicate architecture information. This work investigates the nature of architecture information communication (i.e., why, who, when, and what) by OSS developers via developer mailing lists. We employed a multiple case study approach to extract and analyze the architecture information communication from the developer mailing lists of two OSS projects, ArgoUML and Hibernate, during their development life-cycle of over 18 years. Our main findings are: (a) architecture negotiation and interpretation are the two main reasons (i.e., why) of architecture communication; (b) the amount of architecture information communicated in developer mailing lists decreases after the first stable release (i.e., when); (c) architecture communications centered around a few core developers (i.e., who); (d) and the most frequently communicated architecture elements (i.e., what) are Architecture Rationale and Architecture Model. There are a few similarities of architecture communication between the two OSS projects. Such similarities point to how OSS developers naturally gravitate towards the four aspects of architecture communication in OSS development.

Qiang Sun, Sirui Li, Tingting Bi et al.

Acquiring structured data from domain-specific, image-based documents such as scanned reports is crucial for many downstream tasks but remains challenging due to document variability. Many of these documents exist as images rather than as machine-readable text, which requires human annotation to train automated extraction systems. We present DocSpiral, the first Human-in-the-Spiral assistive document annotation platform, designed to address the challenge of extracting structured information from domain-specific, image-based document collections. Our spiral design establishes an iterative cycle in which human annotations train models that progressively require less manual intervention. DocSpiral integrates document format normalization, comprehensive annotation interfaces, evaluation metrics dashboard, and API endpoints for the development of AI / ML models into a unified workflow. Experiments demonstrate that our framework reduces annotation time by at least 41\% while showing consistent performance gains across three iterations during model training. By making this annotation platform freely accessible, we aim to lower barriers to AI/ML models development in document processing, facilitating the adoption of large language models in image-based, document-intensive fields such as geoscience and healthcare. The system is freely available at: https://app.ai4wa.com. The demonstration video is available: https://app.ai4wa.com/docs/docspiral/demo.

Tingting Bi, Peng Liang, Antony Tang et al.

Context: Architecture Tactics (ATs) are architectural building blocks that provide general architectural solutions for addressing Quality Attributes (QAs) issues. Mining and analyzing QA-AT knowledge can help the software architecture community better understand architecture design. However, manually capturing and mining this knowledge is labor-intensive and difficult. Objective: Using Stack Overflow (SO) as our source, our main goals are to effectively mine such knowledge; and to have some sense of how developers use ATs with respect to QA concerns from related discussions. Methods: We applied a semi-automatic dictionary-based mining approach to extract the QA-AT posts in SO. With the mined QA-AT posts, we identified the relationships between ATs and QAs. Results: Our approach allow us to mine QA-AT knowledge effectively with an F-measure of 0.865 and Performance of 82.2%. Using this mining approach, we are able to discover architectural synonyms of QAs and ATs used by designers, from which we discover how developers apply ATs to address quality requirements. Conclusions: We make two contributions in this work: First, we demonstrated a semi-automatic approach to mine ATs and QAs from SO posts; Second, we identified little-known design relationships between QAs and ATs and grouped architectural design considerations to aid architects make architecture tactics design decisions.

Tingting Bi, Xin Xia, David Lo et al.

Being able to access software in daily life is vital for everyone, and thus accessibility is a fundamental challenge for software development. However, given the number of accessibility issues reported by many users, e.g., in app reviews, it is not clear if accessibility is widely integrated into current software projects and how software projects address accessibility issues. In this paper, we report a study of the critical challenges and benefits of incorporating accessibility into software development and design. We applied a mixed qualitative and quantitative approach for gathering data from 15 interviews and 365 survey respondents from 26 countries across five continents to understand how practitioners perceive accessibility development and design in practice. We got 44 statements grouped into eight topics on accessibility from practitioners' viewpoints and different software development stages. Our statistical analysis reveals substantial gaps between groups, e.g., practitioners have Direct v.s. Indirect accessibility relevant work experience when they reviewed the summarized statements. These gaps might hinder the quality of accessibility development and design, and we use our findings to establish a set of guidelines to help practitioners be aware of accessibility challenges and benefit factors. We also propose some remedies to resolve the gaps and to highlight key future research directions.

Yanming Yang, Xin Xia, David Lo et al.

Predictive models are one of the most important techniques that are widely applied in many areas of software engineering. There have been a large number of primary studies that apply predictive models and that present well-preformed studies and well-desigeworks in various research domains, including software requirements, software design and development, testing and debugging and software maintenance. This paper is a first attempt to systematically organize knowledge in this area by surveying a body of 139 papers on predictive models. We describe the key models and approaches used, classify the different models, summarize the range of key application areas, and analyze research results. Based on our findings, we also propose a set of current challenges that still need to be addressed in future work and provide a proposed research road map for these opportunities.