Related papers: RepoCoder: Repository-Level Code Completion Throug…

A code completion system suggests future code elements to developers given a partially-complete code snippet. Code completion is one of the most useful features in Integrated Development Environments (IDEs). Currently, most code completion…

Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their…

The evolution of AI coding agents has shifted the frontier from simple snippet completion to autonomous repository-level engineering. However, evaluating these agents remains ill-posed in general code repository generation, where the lack…

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,…

This work introduces self-infilling code generation, a general framework that incorporates infilling operations into auto-regressive decoding. Our approach capitalizes on the observation that recent infilling-capable code language models…

The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs to enhance code…

Large language models (LLMs) have achieved strong performance on code generation, but existing methods still struggle with repository-level code generation under executable validation. Under this evaluation setting, success is determined…

Multimodal large language models (MLLMs) have streamlined front-end interface development by automating code generation. However, these models also introduce challenges in ensuring code quality. Existing approaches struggle to maintain both…

The advancement of large language models has intensified the need to modernize enterprise applications and migrate legacy systems to secure, versatile languages. However, existing code translation benchmarks primarily focus on individual…

Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval. Code retrieval is critically…

Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging. However, current benchmarks primarily emphasize functional relevance while neglecting critical dimensions of software quality.…

The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages, enabling analysis in scenarios where source code is unavailable. This task supports various reverse…

Automatically generating concise, informative comments for source code can lighten documentation effort and accelerate program comprehension. Retrieval-augmented approaches first fetch code snippets with existing comments and then…

Despite recent progress made by large language models in code generation, they still struggle with programs that meet complex requirements. Recent work utilizes plan-and-solve decomposition to decrease the complexity and leverage self-tests…

Large language models (LLMs) have achieved strong performance on code completion tasks in general-purpose programming languages. However, existing repository-level code completion benchmarks focus almost exclusively on software code and…

Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…

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…

Repository-scale code reasoning is a cornerstone of modern AI-assisted software engineering, enabling Large Language Models (LLMs) to handle complex workflows from program comprehension to complex debugging. However, balancing accuracy with…

Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems. Most prior…

The task of generating code solutions for a given programming problem can benefit from the use of pre-trained language models such as Codex, which can produce multiple diverse samples. However, a major challenge for this task is to select…