Related papers: FastCode: Fast and Cost-Efficient Code Understandi…

The rapid advancement of large language models (LLMs) has significantly improved code completion tasks, yet the trade-off between accuracy and computational cost remains a critical challenge. While using larger models and incorporating…

Recent advances in large language models (LLMs) have given rise to powerful coding agents, making it possible for code assistants to evolve into code engineers. However, existing methods still face significant challenges in achieving…

Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constraints. Existing large language model (LLM) approaches face fundamental limitations in this…

Deep learning is being used extensively in a variety of software engineering tasks, e.g., program classification and defect prediction. Although the technique eliminates the required process of feature engineering, the construction of…

LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it…

We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal…

Code search is a widely used technique by developers during software development. It provides semantically similar implementations from a large code corpus to developers based on their queries. Existing techniques leverage deep learning…

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this…

Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented…

As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-augmented generation (RAG) methods typically treat code as…

The recent progress of artificial intelligence(AI) has shown great potentials for alleviating human burden in various complex tasks. From the view of software engineering, AI techniques can be seen in many fundamental aspects of…

Inference-time scaling has emerged as a powerful alternative to parameter scaling for improving language model performance on complex reasoning tasks. While existing methods have shown strong performance gains under fixed compute budgets,…

Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static semantics inference, and dynamic reasoning. Traditional tools are…

Source code segmentation, dividing code into functionally coherent segments, is crucial for knowledge retrieval and maintenance in software development. While enabling efficient navigation and comprehension of large codebases, manual and…

Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and control constraints. When additional reasoning structure helps, and when it instead reduces efficiency…

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…

Repository-level code completion automatically predicts the unfinished code based on the broader information from the repository. Recent strides in Code Large Language Models (code LLMs) have spurred the development of repository-level code…

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…

Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation…

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…