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

Recent advances in large language models (LLMs) have shown that test-time scaling can substantially improve model performance on complex tasks, particularly in the coding domain. Under this paradigm, models use a larger token budget during…

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

This paper presents LogiCode, a novel framework that leverages Large Language Models (LLMs) for identifying logical anomalies in industrial settings, moving beyond traditional focus on structural inconsistencies. By harnessing LLMs for…

Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatial resolution and long temporal context prohibitive. We argue…

Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on…

Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into…

Recent advances in retrieval-augmented generation (RAG) have initiated a new era in repository-level code completion. However, the invariable use of retrieval in existing methods exposes issues in both efficiency and robustness, with a…

This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental byproduct of prompting, we argue that the trade-off between rapid,…

Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting…

Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or…

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing…

Code generation is crucial in software engineering for automating the coding process efficiently. While test-time computation methods show promise, they suffer from high latency due to multiple computation rounds. To overcome this, we…

(Source) code search is widely concerned by software engineering researchers because it can improve the productivity and quality of software development. Given a functionality requirement usually described in a natural language sentence, a…

Modern codebases make it hard for developers and AI coding assistants to find the right source files when answering questions like "How does this feature work?" or "Where was the bug introduced?" Traditional code search (keyword or IR…

Repository-level code generation aims to generate code within the context of a specified repository. Existing approaches typically employ retrieval-augmented generation (RAG) techniques to provide LLMs with relevant contextual information…

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can…

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…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…