# VersiCode: Towards Version-controllable Code Generation

arXiv: https://arxiv.org/abs/2406.07411 · HTML: https://mlsanity.com/paper/2406.07411/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 66 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 30 of 43)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow](https://mlsanity.com/paper/1805.08949/) (2018)
- [Continual Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2402.01364/) (2024)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs](https://mlsanity.com/paper/2402.14903/) (2024)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [DebugBench: Evaluating Debugging Capability of Large Language Models](https://mlsanity.com/paper/2401.04621/) (2024)
- [RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation](https://mlsanity.com/paper/2402.16667/) (2024)
- [AVATAR: A Parallel Corpus for Java-Python Program Translation](https://mlsanity.com/paper/2108.11590/) (2021)
- [CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation](https://mlsanity.com/paper/2310.04951/) (2023)

## Built on by (most cited first, 17 of 17)

- [ReCode: Updating Code API Knowledge with Reinforcement Learning](https://mlsanity.com/paper/2506.20495/) (2025)
- [Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents](https://mlsanity.com/paper/2505.05283/) (2025)
- [RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation](https://mlsanity.com/paper/2503.16922/) (2025)
- [CARD: Towards Conditional Design of Multi-agent Topological Structures](https://mlsanity.com/paper/2603.01089/) (2026)
- [GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models](https://mlsanity.com/paper/2411.05830/) (2024)
- [Large Language Model Unlearning for Source Code](https://mlsanity.com/paper/2506.17125/) (2025)
- [Environment-Aware Code Generation: How far are We?](https://mlsanity.com/paper/2601.12262/) (2026)
- [AutoPLC: Generating Vendor-Aware Structured Text for Programmable Logic Controllers](https://mlsanity.com/paper/2412.02410/) (2024)
- [When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generation](https://mlsanity.com/paper/2512.05341/) (2025)
- [KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation](https://mlsanity.com/paper/2603.07581/) (2026)
- [Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions](https://mlsanity.com/paper/2605.06279/) (2026)
- [SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements](https://mlsanity.com/paper/2607.27409/) (2026)
- [Toward Executable Repository-Level Code Generation via Environment Alignment](https://mlsanity.com/paper/2604.03622/) (2026)
- [Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition](https://mlsanity.com/paper/2606.03657/) (2026)
- [LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models](https://mlsanity.com/paper/2606.25402/) (2026)
- [What Was Once Learned May Need to Be Unlearned: Machine Unlearning for Deprecated API Knowledge in Large Language Models](https://mlsanity.com/paper/2609.25786/) (2026)
- [Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models](https://mlsanity.com/paper/2610.05277/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development, marked by frequent library updates. This gap significantly limits LLMs' deployment in realistic settings. In this paper, we propose two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM). In conjunction, we introduce VersiCode, a comprehensive Python dataset specifically designed to evaluate LLMs on these two tasks, together with a novel evaluation metric, Critical Diff Check (CDC@1), which assesses code generation against evolving API requirements. We conduct an extensive evaluation on VersiCode, which reveals that version-controllable code generation is indeed a significant challenge, even for GPT-4o and other strong frontier models. We believe the novel tasks, dataset, and metric open up a new, important research direction that will further enhance LLMs' real-world applicability. The code and resources can be found at https://github.com/wutong8023/VersiCode.