Papers Code Completion

“Code Completion” 태그가 달린 논문 280편 · 필터 해제

Toward an Agentic Infused Software Ecosystem

2026-02-24 · Mark Marron arxiv

Fully leveraging the capabilities of AI agents in software development requires a rethinking of the software ecosystem itself. To this end, this paper outlines the creation of an Agentic Infused Software Ecosystem (AISE)…

Code Completion

Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes

2026-02-05 · Ulrich Finkler, Irene Manotas, Wei Zhang, Geert Janssen 외 arxiv

Code completion (CC) is a task frequently used by developers when working in collaboration with LLM-based programming assistants. Despite the increased performance of LLMs on public benchmarks, out of the box LLMs still …

Code Completion

Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation

2026-02-04 · Nikita Sorokin, Ivan Sedykh, Valentin Malykh arxiv

Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long contexts. We present Hierarchical Embed…

Code Generation Code Completion

Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding

2026-02-02 · Yuling Shi, Chaoxiang Xie, Zhensu Sun, Yeheng Chen 외 arxiv

Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely o…

Computational Efficiency Code Completion

Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression

2026-01-31 · Jianping Zhong, Guochang Li, Chen Zhi, Junxiao Han 외 arxiv

Large Language Models (LLMs) struggle with long-context code due to window limitations. Existing textual code compression methods mitigate this via selective filtering but often disrupt dependency closure, causing semant…

Question Answering Code Completion

Protecting Private Code in IDE Autocomplete using Differential Privacy

2026-01-30 · Evgeny Grigorenko, David Stanojević, David Ilić, Egor Bogomolov 외 arxiv

Modern Integrated Development Environments (IDEs) increasingly leverage Large Language Models (LLMs) to provide advanced features like code autocomplete. While powerful, training these models on user-written code introdu…

Code Completion

AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion

2026-01-27 · Tianyue Jiang, Yanli Wang, Yanlin Wang, Daya Guo 외 arxiv

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-augm…

Reinforcement Learning Code Completion

Evaluating and Achieving Controllable Code Completion in Code LLM

2026-01-22 · Jiajun Zhang, Zeyu Cui, Lei Zhang, Jian Yang 외 arxiv

Code completion has become a central task, gaining significant attention with the rise of large language model (LLM)-based tools in software engineering. Although recent advances have greatly improved LLMs' code completi…

Code Completion

Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

2026-01-20 · Mohamad Salim, Jasmine Latendresse, SayedHassan Khatoonabadi, Emad Shihab arxiv

LLM-based Multi-Agent (LLM-MA) systems are increasingly applied to automate complex software engineering tasks such as requirements engineering, code generation, and testing. However, their operational efficiency and res…

Code Generation Code Completion

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning

2026-01-19 · Jiajun Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang 외 arxiv

The dominant Fill-in-the-Middle (FIM) paradigm for code completion is constrained by its rigid inability to correct contextual errors and reliance on unaligned, insecure Base models. While Chat LLMs offer safety and Agen…

Code Completion

DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models

2026-01-17 · Adarsh Kumarappan, Pareesa Ameneh Golnari, Wen Wen, Xiaoyu Liu 외 arxiv

DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,800 evaluation instances across six programming languages and six task categori…

Code Generation Code Completion

Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs

2026-01-15 · Ali Al-Kaswan, Claudio Spiess, Prem Devanbu, Arie van Deursen 외 arxiv

Large language models are increasingly used for code generation and debugging, but their outputs can still contain bugs, that originate from training data. Distinguishing whether an LLM prefers correct code, or a familia…

Code Generation Code Completion

MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark

2026-01-07 · Qingyun Zou, Jiahao Cui, Nuo Chen, Bingsheng He 외 arxiv

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 s…

Code Completion

EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion

2025-12-29 · Zhen Liang, Hai Huang, Zhengkui Chen arxiv

Large language models (LLMs), such as ChatGPT, have achieved remarkable success across a wide range of fields. However, their trustworthiness remains a significant concern, as they are still susceptible to jailbreak atta…

Code Completion

DUET: Agentic Design Understanding via Experimentation and Testing

2025-12-06 · Gus Henry Smith, Sandesh Adhikary, Vineet Thumuluri, Karthik Suresh 외 arxiv

AI agents powered by large language models (LLMs) are being used to solve increasingly complex software engineering challenges, but struggle with hardware design tasks. Register Transfer Level (RTL) code presents a uniqu…

Code Completion

Quantitative Analysis of Technical Debt and Pattern Violation in Large Language Model Architectures

2025-12-03 · Tyler Slater arxiv

As Large Language Models (LLMs) transition from code completion tools to autonomous system architects, their impact on long-term software maintainability remains unquantified. While existing research benchmarks functiona…

Code Completion

Proactive Agentic Whiteboards: Enhancing Diagrammatic Learning

2025-12-01 · Suveen Ellawela, Sashenka Gamage, Dinithi Dissanayake arxiv

Educators frequently rely on diagrams to explain complex concepts during lectures, yet creating clear and complete visual representations in real time while simultaneously speaking can be cognitively demanding. Incomplet…

Code Completion

Effective Code Membership Inference for Code Completion Models via Adversarial Prompts

2025-11-19 · Yuan Jiang, Zehao Li, Shan Huang, Christoph Treude 외 arxiv

Membership inference attacks (MIAs) on code completion models offer an effective way to assess privacy risks by inferring whether a given code snippet was part of the training data. Existing black- and gray-box MIAs rely…

Code Completion

Automating Hardware Design and Verification from Architectural Papers via a Neural-Symbolic Graph Framework

2025-11-08 · Haoyue Yang, Xuanle Zhao, Yujie Liu, Zhuojun Zou 외 arxiv

The reproduction of hardware architectures from academic papers remains a significant challenge due to the lack of publicly available source code and the complexity of hardware description languages (HDLs). To this end, …

Code Completion

Practical Code RAG at Scale: Task-Aware Retrieval Design Choices under Compute Budgets

2025-10-23 · Timur Galimzyanov, Olga Kolomyttseva, Egor Bogomolov arxiv

We study retrieval design for code-focused generation tasks under realistic compute budgets. Using two complementary tasks from Long Code Arena -- code completion and bug localization -- we systematically compare retriev…

Computational Efficiency Code Completion