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

Code generation is a latency-sensitive task that demands high timeliness. However, with the growing interest and inherent difficulty in repository-level code generation, most existing code generation studies focus on improving the…

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…

Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level…

In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself. FastCoT uses a size-varying context window whose size changes with…

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly…

Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code…

Understanding the purpose of source code is a critical task in software maintenance, onboarding, and modernization. While large language models (LLMs) have shown promise in generating code explanations, they often lack grounding in the…

Retrieval-Augmented Generation (RAG) frameworks aim to enhance Code Language Models (CLMs) by including another module for retrieving relevant context to construct the input prompt. However, these retrieval modules commonly use semantic…

Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tuning or reinforcement learning. While Chain-of-Thought (CoT)…

While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…

Quantitative research increasingly relies on unstructured financial content such as filings, earnings calls, and research notes, yet existing LLM and RAG pipelines struggle with point-in-time correctness, evidence attribution, and…

Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code…

Code often suffers from performance bugs. These bugs necessitate the research and practice of code optimization. Traditional rule-based methods rely on manually designing and maintaining rules for specific performance bugs (e.g., redundant…

Recently deep learning based Natural Language Processing (NLP) models have shown great potential in the modeling of source code. However, a major limitation of these approaches is that they take source code as simple tokens of text and…

The goal of natural language semantic code search is to retrieve a semantically relevant code snippet from a fixed set of candidates using a natural language query. Existing approaches are neither effective nor efficient enough towards a…

Code intelligence is an emerging domain in software engineering, aiming to improve the effectiveness and efficiency of various code-related tasks. Recent research suggests that incorporating contextual information beyond the basic original…

The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to…

Accurate requirement-to-code traceability is crucial for software maintenance. However, existing IR- and embedding-based methods are heavily dependent on lexical similarity, often yielding incomplete or inconsistent links across projects…

Context window efficiency is a practical constraint in large language model (LLM)-based developer tools. Paulsen [12] shows that all tested models degrade in accuracy well before their advertised context limits the Maximum Effective Context…

Code completion can help developers improve efficiency and ease the development lifecycle. Although code completion is available in modern integrated development environments (IDEs), research lacks in determining what makes a good context…