Code Language Models

Follow this topic Ask about this topic

Code language models are studied for tasks including code completion, program understanding, debugging, translation, and repository-level software engineering. Common approaches combine code pretraining and instruction tuning with fill-in-the-middle training, retrieval, and feedback from execution, tests, or reinforcement learning. Evaluation ranges from unit-test benchmarks such as HumanEval to repository repair tasks such as SWE-bench, alongside multilingual, security, and robustness tests. A central challenge is that benchmark success does not always predict reliable behavior on complex code, unfamiliar instructions, or real-world security risks.

Latest papers

115 papers10 papers in the last four weeks, down 9% on the four weeks before. 0.1% of all new papers.

Teaching Language Models How to Code Like Learners: Conversational Serialization for Student Simulation
Apr 12, 2026Charles Koutcheme, Juho Leinonen, Arto HellasAI in Education Code Language Models
Aalto University, Espoo, Finland
Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding
Apr 9, 2026Pengfei He, Shaowei Wang, Tse-Hsun Chen +1Code Language Models Language Model Pretraining
Department of Computer Science, University of Manitoba, Winnipeg, Canada · School of Engineering and Computer Science, Concordia University, Montreal, Canada · School of Computer Science, University of Windsor, Windsor, Canada
Chinese Language Is Not More Efficient Than English in Vibe Coding: A Preliminary Study on Token Cost and Problem-Solving Rate
Apr 6, 2026Simiao Ren, Xingyu Shen, Yuchen Zhou +3LLM Inference Efficiency Multilingual Code Generation
Tsang · ∗,†Scam.ai
Poisoned Identifiers Survive LLM Deobfuscation: A Case Study on Claude Opus 4.6
Apr 5, 2026Luis Guzmán LorenzoCode Language Models Adversarial Robustness of Language Models
From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion
Apr 2, 2026Liang Zhu, Haolin Chen, Lidong Zhao +1Code Generation LLM Uncertainty Estimation
1Tencent, Shenzhen, China
Composer 2 Technical Report
Mar 25, 2026Cursor Research, :, Aaron Chan +53Code Language Models Software Engineering Agents
Steering Code LLMs with Activation Directions for Language and Library Control
Mar 24, 2026Md Mahbubur Rahman, Arjun Guha, Harshitha MenonLanguage Model Steering Code Language Models
Iowa State University · Northeastern University · Lawrence Livermore National Laboratory
InCoder-32B: Code Foundation Model for Industrial Scenarios
Mar 17, 2026Jian Yang, Wei Zhang, Jiajun Wu +25Compiler Optimization Code Language Models
Beihang University · IQuest Research · Shanghai Jiao Tong University +6
IQuest-Coder-V1 Technical Report
Mar 17, 2026Jian Yang, Wei Zhang, Shawn Guo +35Recurrent Language Models Code Language Models
Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
Mar 11, 2026Maximilian Wendlinger, Daniel Kowatsch, Konstantin Böttinger +1Secure Code Generation Code Language Models
Cognitive Security Technologies Fraunhofer Institute for Applied and Integrated Security Garching near Munich, Germany
H2LooP Spark Preview: Continual Pretraining of Large Language Models for Low-Level Embedded Systems Code
Mar 11, 2026Amit Singh, Vedant Nipane, Pulkit Agrawal +2Code Language Models LLM Code Generation
Towards a Neural Debugger for Python
Mar 10, 2026Maximilian Beck, Jonas Gehring, Jannik Kossen +1Code Language Models
Johannes Kepler University Linz, Institute for Machine Learning · Meta FAIR CodeGen Team
Code Fingerprints: Disentangled Attribution of LLM-Generated Code
Mar 4, 2026Jiaxun Guo, Ziyuan Yang, Mengyu Sun +3Language Model Fingerprinting Code Language Models
School of Cyber Science and Engineering, Sichuan University, Chengdu, China
FastCode: Fast and Cost-Efficient Code Understanding and Reasoning
Mar 1, 2026Zhonghang Li, Zongwei Li, Yuxuan Chen +5Efficient Language Model Reasoning Software Engineering
The University of Hong Kong · Huawei Noah’s Ark Lab
Qwen3-Coder-Next Technical Report
Feb 28, 2026Ruisheng Cao, Mouxiang Chen, Jiawei Chen +17Code Language Models AI Coding Agents
EyeLayer: Integrating Human Attention Patterns into LLM-Based Code Summarization
Feb 25, 2026Jiahao Zhang, Yifan Zhang, Kevin Leach +1Code Language Models Text Summarization
Vanderbilt University, Nashville, Tennessee, USA
How Robustly do LLMs Understand Execution Semantics?
Feb 24, 2026Claudio Spiess, Prem Devanbu, Earl T. BarrCode Language Models Language Model Robustness
UC Davis, Davis, California, USA · University College London, London, UK
SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories
Jan 20, 2026Aditya Bharat Soni, Rajat Ghosh, Vaishnavi Bhargava +2LLM Post-Training Automated Test Generation
Carnegie Mellon University · Nutanix · Stanford University
AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans
Sep 26, 2025Yangtian Zi, Zixuan Wu, Aleksander Boruch-Gruszecki +2Software Engineering Agents Human-AI Collaboration
Northeastern University Boston, MA, United States
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention
Aug 22, 2025Yifan Zhang, Chen Huang, Yueke Zhang +5Code Translation LLM Fine-Tuning
Vanderbilt University1 · National University of Singapore2 · University of Notre Dame3
IFEvalCode: Controlled Code Generation
Jul 30, 2025Jian Yang, Wei Zhang, Shukai Liu +9Code Generation Code Language Models
Beihang University · M-A-P · OPPO
Are AI Coders Snitches? An Empirical Study of Pretraining Data Detection on Code Large Language Models
Jul 23, 2025Tianlin Li, Yunxiang Wei, Zhiming Li +5LLM Evaluation Code Language Models
Nanyang Technological University Singapore · Zhejiang University China · Peng Cheng Laboratory China +2
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
Jun 25, 2025Wenjie Jacky Mo, Qin Liu, Xiaofei Wen +5Adversarial Prompt Generation LLM Red Teaming
University of California, Davis · University of Southern California
LLMs are Brittle to Simple Code Transformations: Introducing CETBench - A Benchmark for Code-Equivalence Checking
Jun 4, 2025Neeva Oza, Ishaan Govil, Parul Gupta +3LLM Evaluation Language Model Robustness
Indian Institute of Technology Delhi · IBM Research AI
Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language Models
Mar 9, 2025Batu Guan, Xiao Wu, Yuanyuan Yuan +1Benchmark Design Data Contamination in Language Models
The Chinese University of Hong Kong · Huazhong University of Science and Technology · ETH Zurich

Apr 12, 2026J/K move · Enter open · S save

Teaching Language Models How to Code Like Learners: Conversational Serialization for Student Simulation

Charles Koutcheme, Juho Leinonen, Arto Hellas

Aalto University, Espoo, Finland

AI in Education Code Language Models Programming Education

Open paper AskPDF arXiv

Artificial students -- models that simulate how learners act and respond within educational systems -- are a promising tool for evaluating tutoring strategies and feedback mechanisms at scale. However, most existing approaches rely on prompting large, proprietary language models, limiting adaptability to specific courses and raising concerns around privacy, cost, and dependence. In this work, we propose a framework for training open-weight artificial programming learners directly from authentic student process data. Our approach serializes temporal log traces into a conversational format, representing each student's problem-solving process as a dialogue between the learner and their automated assessment system. Student code submissions and environment feedback, such as test outcomes, grades, and error traces, form alternating conversational turns, enabling models to learn from the iterative debugging process. We additionally introduce a training pipeline combining supervised fine-tuning with preference optimization to align models with authentic student debugging behavior. We evaluate our framework by training Qwen models at 4B and 8B scales on a large-scale dataset of real student submissions to Python programming assignments. Our results show that incorporating environment feedback strengthens models' ability to replicate student debugging behavior, improving over both prior code-only approaches and prompted large language models baselines in functional alignment and code similarity. We release our code to support reproducibility.