ADATracer is presented, a software traceability tool designed to recover links between natural language requirements, Ada source files, version-control commits, and issue-tracking artifacts, and an Ada-aware parser that accounts for language features such as package specifications, bodies, and strong typing.
Abstract
Traceability is an important part of safety-critical software development in areas such as avionics, space, and automotive engineering. Ada is often used in these systems. It shows how requirements are implemented in code and how changes are reflected in commits and issue reports. Automated traceability tools for Ada are not as common as those for other programming languages. Currently, the systematic linking of requirements to Ada source files, version-control history, and issue artifacts is often a manual process that requires effort to maintain throughout the software lifecycle. We present ADATracer, a software traceability tool designed to recover links between natural language requirements, Ada source files, version-control commits, and issue-tracking artifacts. The tool uses keyword-based retrieval, semantic vector embeddings, and a Neo4j-based knowledge graph. It includes an Ada-aware parser that accounts for language features such as package specifications, bodies, and strong typing. ADATracer supports traceability recovery and graph-based exploration, allowing for the inspection of evidence chains from requirements to implementation and issue resolution. We apply ADATracer to the open-source Ada Web Application (AWA) framework, where the tool identifies traceability links. This work facilitates traceability in certification-driven Ada development and provides a framework for further study in safety-critical software systems. The source code and demonstration video are publicly available at https://github.com/rishalab/ADATracer and https://youtu.be/sb66cEffF-o.
The results indicate that language-model assistance can add value in regulated automotive requirements workflows when it is embedded in deterministic, provenance-rich, and expert-governed processes.
In modern software development, the rapid advancement of Large Language Models (LLMs) has made the end-to-end transformation of Natural Language Requirements (NLRs) into executable repository-level code increasingly feasible. However, existing approaches typically rely on simplified instructions (e.g., single-sentence descriptions), failing to reflect complex software development scenarios. Moreover, they lack explicit requirement traceability mechanisms, making it difficult to precisely align and validate generated code against original requirements. To address these limitations, we propose TraceDev, a multi-agent framework for automated software development grounded in use cases that contain multiple functional points and complex semantics. TraceDev employs five role-specific agents, including a Requirement Refiner, Designer, Developer, Tester, and Validator. Notably, the Validator Agent constructs and maintains a heterogeneous traceability graph that links requirements, design models, and code artifacts for interacting with the preceding four agents. The traceability graph maintains consistency across various artifacts and serves as a structured context for efficient memory management, supporting reliable repository-level code generation. We evaluate TraceDev on two widely used datasets (including 125 use cases) compared with two state-of-the-art approaches. On the ETOUR dataset, TraceDev achieves a success rate of 53.63\%, outperforming baseline approaches by up to 186.63\%. A similar trend is observed on the SMOS dataset, where TraceDev attains a success rate of 56.82\%, exceeding baseline approaches by up to 340.80\%. These results demonstrate the effectiveness of TraceDev in repository-level code generation from requirements.
Mingyu Chen, Yakun Zhang, Zihao Xie et al.· 0 citations
Overall, this survey provides a structured characterization of the current state of AIware testing research and identifies key structural challenges that must be addressed to support lifecycle-aware, reliable AIware systems.
K. Gonzalez, Mariam El Mezouar· AIware· 0 citations
The paper is trying to deeply analyze the pros and cons of implementing GenAI into software development, analysing current applications used in software development life cycle (SDLC), drawing upon case studies and programmer experience, and examining effect on code quality, team working and project timeline.
P. Arun, Jagdale, Deepti Ameta et al.· Economic Sciences· 0 citations
Agentic systems have been gaining traction in solving software engineering tasks. These tasks span from writing documentation, fixing faults in the codebase, and developing new features. A promising application of LLM agents is addressing software "issues", with an issue capturing a unit of improvement needed in a software project. Issues can be detected and constructed by static analysis tools, such as SonarQube. Static analysis tools frequently generate a substantial number of reports related to security vulnerabilities and code quality, imposing a significant manual workload on developers. With the advances in agentic AI, there is potential to automatically remediate these issues, thereby reducing developer effort. In this paper, we present our experience and lessons learned in adapting the AutoCodeRover program improvement agent to automatically propose patches for issues reported by SonarQube. We name this new agent SonarQube Remediation Agent, specialized for fixing SonarQube issues. SonarQube Remediation Agent is designed to be capable of interacting with mission-critical codebases in a secure and trustworthy manner. We discuss our approach in tackling practical challenges such as handling large volumes of issues and designing seamless user interactions. SonarQube Remediation Agent is integrated into the software development lifecycle by suggesting patches during the pull request review workflow, enabling developers to efficiently improve software quality and security with SonarQube.
Martin Mirchev, Ridwan Shariffdeen, Haifeng Ruan et al.· SIGSOFT FSE Companion· 1 citation
Issue localization, which identifies code locations requiring modification from issue descriptions, is a critical step in automated software maintenance. Existing approaches predominantly attempt to directly align issue descriptions with code elements, yet often struggle due to the inherent abstraction gap between the issue description and code implementation. Seeking alternative signals, our theoretical analysis suggests that test suites can serve as executable proxies for requirements, reducing localization uncertainty by 7.73 bits of entropy on average. A large-scale empirical study on 18 repositories validates this premise: existing tests cover 96.98\% of ground-truth files, and the two-hop pathway yields stronger semantic connectivity than direct matching in 82.4\% of cases. Despite their potential, leveraging tests for localization faces two key challenges: the semantic gap separating issue descriptions from test identifiers, and the substantial noise in execution traces from infrastructure code. To address these, we propose IssueExec, which bridges the semantic gap through domain-knowledge-enhanced test representations and filters noise via hierarchical trace analysis. Experiments on SWE-bench Lite show that IssueExec achieves state-of-the-art performance, improving function-level Recall@1 by 41.57\% over the strongest baseline. When integrated into the Agentless pipeline, IssueExec resolves 17.72\% more issues, demonstrating practical downstream benefits.
Jiawei Liu, Yun Lin, Chenyan Liu et al.· 0 citations