Related papers: MapCoder: Multi-Agent Code Generation for Competit…
Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…
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…
Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…
Recent advancements in large language models (LLMs) have greatly improved code generation, specifically at the function level. For instance, GPT-4o has achieved a 91.0\% pass rate on HumanEval. However, this draws into question the adequacy…
Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…
Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLMs for automated bug…
Refactoring is a constant activity in software development and maintenance. Scale and maintain software systems are based on code refactoring. However, this process is still labor intensive, as it requires programmers to analyze the…
Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program…
Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance. However, previous Code LLMs are typically fine-tuned on single-source data with limited quality…
Large language models (LLMs) have significantly improved code generation, particularly in one-pass code generation. However, most existing approaches focus solely on generating code in a single programming language, overlooking the…
This paper presents SimulatorCoder, an agent powered by large language models (LLMs), designed to generate and optimize deep neural network (DNN) accelerator simulators based on natural language descriptions. By integrating domain-specific…
Converting user interfaces into code (UI2Code) is a crucial step in website development, which is time-consuming and labor-intensive. The automation of UI2Code is essential to streamline this task, beneficial for improving the development…
This study evaluates the efficiency of code generation by Large Language Models (LLMs) and measures their performance against human-crafted solutions using a dataset from Leetcode. We compare 18 LLMs, considering factors such as model…
Large language models (LLMs) have increasingly been applied to automatic programming code generation. This task can be viewed as a language generation task that bridges natural language, human knowledge, and programming logic. However, it…
A common practice in large language model (LLM) usage for complex analytical tasks such as code generation, is to sample a solution for the entire task within the model's context window. Previous works have shown that subtask decomposition…
As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long…
Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we present CodeCompose, an AI-assisted code authoring tool…
Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed,…
Large language models (LLMs) have demonstrated unparalleled prowess in mimicking human-like text generation and processing. Among the myriad of applications that benefit from LLMs, automated code generation is increasingly promising. The…
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…