Related papers: CodeScout: Contextual Problem Statement Enhancemen…
Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored. Due to the size and complexities of systems code, making changes to a systems…
GenAI-based coding assistants have disrupted software development. The next generation of these tools is agent-based, operating with more autonomy and potentially without human oversight. Like human developers, AI agents require contextual…
Effective prompting of generative AI is challenging for many users, particularly in expressing context for comprehension tasks such as explaining spreadsheet formulas, Python code, and text passages. Prompt middleware aims to address this…
Domain experts possess tacit knowledge that they cannot easily articulate through explicit specifications. When experts modify AI-generated artifacts by correcting terminology, restructuring arguments, and adjusting emphasis, these edits…
Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily…
Fixing software bugs and adding new features are two of the major maintenance tasks. Software bugs and features are reported as change requests. Developers consult these requests and often choose a few keywords from them as an ad hoc query.…
Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…
Software development is a cognitively intensive process requiring multitasking, adherence to evolving workflows, and continuous learning. With the rise of large language model (LLM)-based tools, such as conversational agents (CAs), there is…
Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to…
Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from enclosed environments…
Spellchecking is one of the most fundamental and widely used search features. Correcting incorrectly spelled user queries not only enhances the user experience but is expected by the user. However, most widely available spellchecking…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
E-commerce queries are often short and ambiguous. Consequently, query understanding often uses query rewriting to disambiguate user-input queries. While using e-commerce search tools, users tend to enter multiple searches, which we call…
Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…
Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly…
Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…
Pretrained code language models have enabled great progress towards program synthesis. However, common approaches only consider in-file local context and thus miss information and constraints imposed by other parts of the codebase and its…
Software engineers resolving repository-level issues do not treat existing tests as immutable correctness oracles. Instead, they iteratively refine both code and the tests used to characterize intended behavior, as new modifications expose…
Code comments are significantly helpful in comprehending software programs and also aid developers to save a great deal of time in software maintenance. Code comment generation aims to automatically predict comments in natural language…
We introduce PATHWAYS, a benchmark of 250 multi-step decision tasks that test whether web-based agents can discover and correctly use hidden contextual information. Across both closed and open models, agents typically navigate to relevant…