Related papers: CodeScout: Contextual Problem Statement Enhancemen…
Agentic systems have been widely studied to automate software engineering jobs such as bug fixing. As these systems increasingly tackle complex tasks, understanding where and why they fail becomes essential for iterative refinement and…
AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-agent orchestration.…
Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…
The query suggestion or auto-completion mechanisms help users to type less while interacting with a search engine. A basic approach that ranks suggestions according to their frequency in the query logs is suboptimal. Firstly, many candidate…
Software development is a complex activity which depends on diverse technologies and people's expertise. The approaches to developing software highly depend on these different characteristics, which are the context developers are subject…
The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safety. Existing forensic methods mainly rely on visual cues and lack evidence-based reasoning to…
Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software engineering tasks that require external knowledge or broader repository-level changes. We…
The rapid pace of large-scale software development places increasing demands on traditional testing methodologies, often leading to bottlenecks in efficiency, accuracy, and coverage. We propose a novel perspective on software testing by…
Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on end-to-end tasks such as issue resolution truly reflects repository context reasoning, the…
Code completion aims at speeding up code writing by recommending to developers the next tokens they are likely to type. Deep Learning (DL) models pushed the boundaries of code completion by redefining what these coding assistants can do: We…
Recent advancements in AI and edge computing have accelerated the development of machine-centric applications (MCAs), such as smart surveillance systems. In these applications, video cameras and sensors offload inference tasks like license…
LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action…
Modern AI agents optimize programs by refactoring source code to trigger trusted compiler transformations. This preserves program semantics and reduces source code pollution, making the program easier to maintain and portable across…
Query spelling correction is an important function of modern search engines since it effectively helps users express their intentions clearly. With the growing popularity of speech search driven by Automated Speech Recognition (ASR)…
Software Development (SD) is remarkably dynamic and is critically dependent on the knowledge acquired by the project's software developers as the project progresses. Software developers need to understand large amounts of information…
We introduce DeepSearchQA, a 900-prompt benchmark for evaluating agents on difficult multi-step information-seeking tasks across 17 different fields. Unlike traditional benchmarks that target single answer retrieval or broad-spectrum…
Code review is a cornerstone of software quality assurance, and recent advances in Large Language Models (LLMs) have shown promise in its automation. However, existing benchmarks for LLM-based code review face three major limitations. Lack…
Maintaining large-scale, multilingual codebases hinges on accurately localizing issues, which requires mapping natural-language error descriptions to the relevant functions that need to be modified. However, existing ranking approaches are…
Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for…
Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a shared embedding space and retrieve results based on vector similarity. Despit strong…