软件工程
Large language models (LLMs) have shown growing potential in software engineering, yet few benchmarks evaluate their ability to repair software during migration across instruction set architectures (ISAs). Cross-ISA migration, such as…
Classical software verification and validation techniques, such as procedural audits, formal methods, or model documentation, are the traditional mechanisms used to achieve the verifiable accountability now required by regulations like the…
Automatically repairing software issues remains a fundamental challenge at the intersection of software engineering and AI. Although recent advances in Large Language Models (LLMs) have demonstrated potential for repository-level repair…
Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, especially as agentic coding frameworks increase the rate of code production. Over the last decade, a…
Rapid advances in the field of Large Language Models (LLMs) have made LLM-based code generation an important area for investigation. An LLM-based code generator takes a prompt as input and produces code that implements the requirements…
Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adherence to structural constraints, such as architectural…
Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party library (TPL) imports annotated with specific version identifiers. These version choices can…
Developers often make similar mistakes across code locations implementing related functionalities. These locations, called siblings, share similar issues and require similar fixes. Accurately identifying siblings and consistently repairing…
We introduce an evaluation framework of 500 C verification tasks across five property types (memory safety, overflow, termination, reachability, data races) built on SV-COMP 2025, and evaluate 14 models across six families. We find that…
Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-managed: one agent writes a repository, and later agents inspect, audit, or extend it…
As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full…
Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale with the number of tasks, motivating a unified multi-task RL…
The automated recognition of algorithm implementations can support many software maintenance and re-engineering activities by providing knowledge about the concerns present in the code base. Moreover, recognizing inefficient algorithms like…
Large Language Models are increasingly used in software engineering, but both code generation and its evaluation remain predominantly English-centric. This leaves a major gap in our understanding of how well current tools support…
The security of AI-generated code remains a major obstacle to its widespread adoption. Although code generation models achieve strong performance on functional benchmarks, their outputs frequently contain bugs and security weaknesses that…
Large language model (LLM)-based coding assistants have made substantial progress, yet most systems remain reactive, requiring developers to explicitly formulate their needs. Proactive coding assistants aim to infer latent developer intent…
As AI coding agents become embedded in software development workflows, developers are beginning to operationalize ethical principles by encoding behavioral rules into repository-level context files for AI agents, such as AGENTS.md files.…
Continuous Integration (CI) systems often run many builds concurrently. In this setting, a legitimate build failure may not be caused by the code push that triggered it. Such unrelated build failures can waste developer effort because…
The rapid adoption of AI coding agents has produced a dominant workflow pattern -- often called "vibe coding" -- that prioritizes speed of implementation over deliberate preparation. We argue that this approach creates a systematic…
Large language models (LLMs) frequently generate defective outputs in code generation tasks, ranging from logical bugs to security vulnerabilities. While these generation failures are often treated as model-level limitations, empirical…