Related papers: CodeFuse-Query: A Data-Centric Static Code Analysi…

When working in large and complex codebases, developers face challenges using \textit{Find Usages} to understand how to reuse classes and methods. To better understand these challenges, we conducted a small exploratory study with 4…

Despite the surge of interest in autonomous scientific discovery (ASD) of software artifacts (e.g., improved ML algorithms), current ASD systems face two key limitations: (1) they largely explore variants of existing codebases or similarly…

Large Language Models (LLMs) have shown promising performance in code generation. However, how to reliably evaluate code generated by LLMs remains an unresolved problem. This paper presents CodeJudge, a code evaluation framework that…

Code editing constitutes a fundamental practice in software development, wherein developers modify existing codebases according to natural language requirements. Accurate code editing necessitates a comprehensive understanding of both the…

Code localization constitutes a key bottleneck in automated software development pipelines. While concurrent tool execution can enhance discovery speed, current agents demonstrate a 34.9\% redundant invocation rate, which negates…

Nowadays, software testing professionals are commonly required to develop coding skills to work on test automation. One essential skill required from those who code is the ability to implement code refactoring, a valued quality aspect of…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…

Consider the case where a programmer has written some part of a program, but has left part of the program (such as a method or a function body) incomplete. The goal is to use the context surrounding the missing code to automatically 'figure…

The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performance. With application domains ranging from warehouse logistics to windfarm management, co-design…

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…

Finding the optimal set of cloud resources to deploy a given workload at minimal cost while meeting a defined service level agreement is an active area of research. Combining tens of parameters applicable across a large selection of…

Modern large language model-based reasoning systems frequently recompute similar reasoning steps across tasks, wasting computational resources, inflating inference latency, and limiting reproducibility. These inefficiencies underscore the…

With an increasing number of value-flow properties to check, existing static program analysis still tends to have scalability issues when high precision is required. We observe that the key design flaw behind the scalability problem is that…

Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with…

Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging. However, current benchmarks primarily emphasize functional relevance while neglecting critical dimensions of software quality.…

While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this…

Large Language Models (LLMs) have demonstrated remarkable performance on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and generation capacities…

Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches face significant challenges, including reliance on…

Representing source code in a generic input format is crucial to automate software engineering tasks, e.g., applying machine learning algorithms to extract information. Visualizing code representations can further enable human experts to…

To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework deconstructs…