English
Related papers

Related papers: Challenge on Optimization of Context Collection fo…

200 papers

As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-augmented generation (RAG) methods typically treat code as…

Software Engineering · Computer Science 2025-12-05 Xinkui Zhao , Rongkai Liu , Yifan Zhang , Chen Zhi , Lufei Zhang , Guanjie Cheng , Yueshen Xu , Shuiguang Deng , Jianwei Yin

Automated code review (CR) is a key application for Large Language Models (LLMs), but progress is hampered by a "reality gap": existing benchmarks evaluate models on isolated sub-tasks using simplified, context-poor data. This fails to…

Software Engineering · Computer Science 2025-10-24 Hanyang Guo , Xunjin Zheng , Zihan Liao , Hang Yu , Peng DI , Ziyin Zhang , Hong-Ning Dai

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…

CodeLLMs have demonstrated remarkable advancements in software engineering tasks. However, while these models can generate functionally correct code, they often produce code that is inefficient in terms of runtime. This inefficiency is…

Software Engineering · Computer Science 2024-12-24 Chengran Yang , Hong Jin Kang , Jieke Shi , David Lo

During complex knowledge work, people engage in iterative sensemaking: interpreting information, connecting ideas, and refining their understanding. Yet in current human-AI collaboration, these cognitive processes are difficult to share and…

Human-Computer Interaction · Computer Science 2026-04-14 Yoonsu Kim , Chanbin Park , Kihoon Son , Saelyne Yang , Juho Kim

Recent advancements in Large Language Models (LLMs) and their utilization in code generation tasks have significantly reshaped the field of software development. Despite the remarkable efficacy of code completion solutions in mainstream…

Software Engineering · Computer Science 2024-06-12 Bohdan Petryshyn , Mantas Lukoševičius

Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various…

Computation and Language · Computer Science 2024-02-02 Yilun Zhu , Joel Ruben Antony Moniz , Shruti Bhargava , Jiarui Lu , Dhivya Piraviperumal , Site Li , Yuan Zhang , Hong Yu , Bo-Hsiang Tseng

LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens,…

Software Engineering · Computer Science 2026-05-13 Kirill Gelvan , Igor Slinko , Felix Steinbauer , Egor Bogomolov , Florian Kofler , Yaroslav Zharov

With the exponential growth of AI tools that generate source code, understanding software has become crucial. When developers comprehend a program, they may refer to additional contexts to look for information, e.g. program documentation or…

Software Engineering · Computer Science 2024-02-07 Huy Nguyen , Christoph Treude , Patanamon Thongtanunam

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs…

Computation and Language · Computer Science 2017-04-26 Maxim Rabinovich , Mitchell Stern , Dan Klein

Program code as a data source is gaining popularity in the data science community. Possible applications for models trained on such assets range from classification for data dimensionality reduction to automatic code generation. However,…

Software Engineering · Computer Science 2022-10-31 Anastasia Drozdova , Polina Guseva , Ekaterina Trofimova , Anna Scherbakova , Andrey Ustyuzhanin

As code generation becomes increasingly central to improving software development efficiency, modern code models are largely trained and evaluated on code with natural-language descriptions. In real projects, developers often implement…

Software Engineering · Computer Science 2026-05-19 Chen Liu , Qingyuan Liang , Hanwen Zhang , Zeyu Sun , Yakun Zhang , Lu Zhang

Competitive programming has become a popular way for programmers to test their skills. Large-scale online programming contests attract millions of experienced programmers to compete against each other. Competition-level programming problems…

Software Engineering · Computer Science 2022-06-07 Jialu Zhang , De Li , John C. Kolesar , Hanyuan Shi , Ruzica Piskac

Artificial Intelligence (AI)-assisted coding environments operate within finite context windows of 128,000-1,000,000 tokens (as of early 2026), yet existing tools offer limited support for monitoring and optimizing token consumption. As…

Software Engineering · Computer Science 2026-04-10 Vahid Farajijobehdar , İlknur Köseoğlu Sarı , Nazım Kemal Üre , Engin Zeydan

Large language models have been successfully applied to programming assistance tasks, such as code completion, code insertion, and instructional code editing. However, these applications remain insufficiently automated and struggle to…

Computation and Language · Computer Science 2025-05-14 Hao Jiang , Qi Liu , Rui Li , Shengyu Ye , Shijin Wang

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…

Software Engineering · Computer Science 2025-10-16 Minh Nguyen

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

Software Engineering · Computer Science 2026-04-16 Jia Feng , Zhanyue Qin , Cuiyun Gao , Ruiqi Wang , Chaozheng Wang , Yingwei Ma , Xiaoyuan Xie

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…

Software Engineering · Computer Science 2026-05-18 Atharva Sehgal , James Hou , Akanksha Sarkar , Ishaan Mantripragada , Swarat Chaudhuri , Jennifer J. Sun , Yisong Yue

With the advances in machine learning, there is a growing interest in AI-enabled tools for autocompleting source code. GitHub Copilot, also referred to as the "AI Pair Programmer", has been trained on billions of lines of open source GitHub…

Software Engineering · Computer Science 2023-04-28 Beiqi Zhang , Peng Liang , Xiyu Zhou , Aakash Ahmad , Muhammad Waseem

Despite the success of large pre-trained language models (LMs) such as Codex, they show below-par performance on the larger and more complicated programming related questions. We show that LMs benefit from the summarized version of…

Computation and Language · Computer Science 2022-10-25 Kirby Kuznia , Swaroop Mishra , Mihir Parmar , Chitta Baral