English
Related papers

Related papers: CursorCore: Assist Programming through Aligning An…

200 papers

The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent and safe behavior in language models (LMs). Despite its…

Coherence is an essential property of well-written texts, that refers to the way textual units relate to one another. In the era of generative AI, coherence assessment is essential for many NLP tasks; summarization, generation, long-form…

Computation and Language · Computer Science 2024-08-14 Aviya Maimon , Reut Tsarfaty

Code completion is widely used by software developers to provide coding suggestions given a partially written code snippet. Apart from the traditional code completion methods, which only support single token completion at minimal positions,…

Software Engineering · Computer Science 2021-06-29 Jingxuan Li , Rui Huang , Wei Li , Kai Yao , Weiguo Tan

The emergence of large language models and their applications as AI agents have significantly advanced state-of-the-art code generation benchmarks, transforming modern software engineering tasks. However, even with test-time computed…

Artificial Intelligence · Computer Science 2025-03-25 Hao-Yuan Chen , Cheng-Pong Huang , Jui-Ming Yao

Transformer-based pre-trained models have recently achieved great results in solving many software engineering tasks including automatic code completion which is a staple in a developer's toolkit. While many have striven to improve the…

Computation and Language · Computer Science 2023-04-25 Tim van Dam , Maliheh Izadi , Arie van Deursen

Large Language Models (LLMs) have become central to automated code generation, yet existing approaches operate within a single-LLM paradigm: one model is selected and applied throughout the entire generation process. We observe that…

Software Engineering · Computer Science 2026-04-21 Huashan Chen , Zhenyu Qi , Haotang Li , Hong Chen , Jinfu Chen , Kebin Peng , In Kee Kim , Kyu Hyung Lee , Sen He , Weiyi Shang

Automatic code completion helps improve developers' productivity in their programming tasks. A program contains instructions expressed via code statements, which are considered as the basic units of program execution. In this paper, we…

Software Engineering · Computer Science 2019-11-19 Son Nguyen , Tien N. Nguyen , Yi Li , Shaohua Wang

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…

Computation and Language · Computer Science 2025-06-02 Fei Bai , Yingqian Min , Beichen Zhang , Zhipeng Chen , Wayne Xin Zhao , Lei Fang , Zheng Liu , Zhongyuan Wang , Ji-Rong Wen

Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into…

Software Engineering · Computer Science 2025-01-08 Jialiang Chen , Kaifa Zhao , Jie Liu , Chao Peng , Jierui Liu , Hang Zhu , Pengfei Gao , Ping Yang , Shuiguang Deng

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Machine Learning · Computer Science 2026-03-30 Alireza Moayedikia , Alicia Troncoso

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple…

Computation and Language · Computer Science 2024-07-04 Hanxu Hu , Simon Yu , Pinzhen Chen , Edoardo M. Ponti

Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using only a subset of the input -- a proxy context -- rather…

Computation and Language · Computer Science 2026-05-25 Miao Li , Irina Saparina , Alexander Gurung , Mirella Lapata

The Agent Conversation Reasoning Engine (ACRE) is intended to aid agent developers to improve the management and reliability of agent communication. To evaluate its effectiveness, a problem scenario was created that could be used to compare…

Multiagent Systems · Computer Science 2014-10-13 David Lillis , Rem W. Collier , Howell R. Jordan

Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited--a critical requirement in real-world software systems. We argue that current…

Software Engineering · Computer Science 2026-05-11 Jiuding Yang , Shengyao Lu , Hongxuan Liu , Shayan Shirahmad Gale Bagi , Zahra Fazel , Tomasz Czajkowski , Di Niu

We introduce CRPE (Code Reasoning Process Enhancer), an innovative three-stage framework for data synthesis and model training that advances the development of sophisticated code reasoning capabilities in large language models (LLMs).…

Software Engineering · Computer Science 2025-05-19 Ningxin Gui , Qianghuai Jia , Feijun Jiang , Yuling Jiao , dechun wang , Jerry Zhijian Yang

The assessment of source code in university education is a central and important task for lecturers of programming courses. In doing so, educators are confronted with growing numbers of students having increasingly diverse prerequisites, a…

Software Engineering · Computer Science 2023-06-09 Clemens Sauerwein , Tobias Antensteiner , Stefan Oppl , Iris Groher , Alexander Meschtscherjakov , Philipp Zech , Ruth Breu

Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation…

Computation and Language · Computer Science 2024-02-01 Yushi Bai , Xin Lv , Jiajie Zhang , Yuze He , Ji Qi , Lei Hou , Jie Tang , Yuxiao Dong , Juanzi Li

Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand…

Programming Languages · Computer Science 2025-06-16 Peter Pirkelbauer , Chunhua Liao

With the significant progress of large reasoning models in complex coding and reasoning tasks, existing benchmarks, like LiveCodeBench and CodeElo, are insufficient to evaluate the coding capabilities of large language models (LLMs) in real…

Computation and Language · Computer Science 2025-06-06 Shiyi Xu , Yiwen Hu , Yingqian Min , Zhipeng Chen , Wayne Xin Zhao , Ji-Rong Wen

Assembly-to-source code translation is a critical task in reverse engineering, cybersecurity, and software maintenance, yet systematic benchmarks for evaluating large language models on this problem remain scarce. In this work, we present…

Software Engineering · Computer Science 2025-12-02 Parisa Hamedi , Hamed Jelodar , Samita Bai , Mohammad Meymani , Roozbeh Razavi-Far , Ali A. Ghorbani