Related papers: Code Researcher: Deep Research Agent for Large Sys…
Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent,…
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a…
The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their performance on certain tasks can be further enhanced by incorporating test-time reasoning techniques. These…
Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting…
Research scientists increasingly rely on implementing software to support their research. While previous research has examined the impact of identifier names on program comprehension in traditional programming environments, limited work has…
Recent developments in Large Language Model (LLM)-based agents have shown impressive capabilities spanning multiple domains, exemplified by deep research systems that demonstrate superior performance on complex information-seeking and…
Recent research has explored the use of Large Language Models (LLMs) for tackling complex graph reasoning tasks. However, due to the intricacies of graph structures and the inherent limitations of LLMs in handling long text, current…
Effective prompt design is essential for improving the planning capabilities of large language model (LLM)-driven agents. However, existing structured prompting strategies are typically limited to single-agent, plan-only settings, and often…
Security code review is a time-consuming and labor-intensive process typically requiring integration with automated security defect detection tools. However, existing security analysis tools struggle with poor generalization, high false…
Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for…
Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse when downsized to…
Automating the adaptation of software engineering (SE) research artifacts across datasets is essential for scalability and reproducibility, yet it remains largely unstudied. Recent advances in large language model (LLM)-based multi-agent…
Crash reports are central to software maintenance, yet many lack the diagnostic detail developers need to debug efficiently. We examine whether large language models can enhance crash reports by adding fault locations, root-cause…
Large Language Models (LLMs) have been widely adopted as task planners for AI agents in sequential decision-making problems, leveraging their extensive world knowledge. However, the gap between their general knowledge and…
Recent advancements in code-fluent Large Language Models (LLMs) enabled the research on repository-level code editing. In such tasks, the model navigates and modifies the entire codebase of a project according to request. Hence, such tasks…
Code localization--identifying precisely where in a codebase changes need to be made--is a fundamental yet challenging task in software maintenance. Existing approaches struggle to efficiently navigate complex codebases when identifying…
Benchmarks for large language models (LLMs) have predominantly assessed short-horizon, localized reasoning. Existing long-horizon suites (e.g. SWE-bench) rely on manually curated issues, so expanding or tuning difficulty demands expensive…
Generating accurate code review comments remains a significant challenge due to the inherently diverse and non-unique nature of the task output. Large language models pretrained on both programming and natural language data tend to perform…
The rapid development of open-source large language models (LLMs) has been truly remarkable. However, the scaling law described in previous literature presents varying conclusions, which casts a dark cloud over scaling LLMs. We delve into…
Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…