CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale

• URL: http://arxiv.org/abs/2502.16645v1
• Date: Sun, 23 Feb 2025 16:46:18 GMT
• Title: CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale
• Authors: Chenlong Wang, Zhaoyang Chu, Zhengxiang Cheng, Xuyi Yang, Kaiyue Qiu, Yao Wan, Zhou Zhao, Xuanhua Shi, Dongping Chen,
• Abstract summary: This paper introduces CODESYNC, a data engine for identifying outdated code patterns.<n>Building upon CODESYNC, we develop CODESYNCBENCH, a benchmark for assessing Large Language Models' ability to stay synchronized with code evolution.
• Score: 39.54772602678732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs. This limitation, stemming from static pre-training datasets, often results in non-executable code or implementations with suboptimal safety and efficiency. To this end, this paper introduces CODESYNC, a data engine for identifying outdated code patterns and collecting real-time code knowledge updates from Python third-party libraries. Building upon CODESYNC, we develop CODESYNCBENCH, a comprehensive benchmark for assessing LLMs' ability to stay synchronized with code evolution, which covers real-world updates for 220 APIs from six Python libraries. Our benchmark offers 3,300 test cases across three evaluation tasks and an update-aware instruction tuning dataset consisting of 2,200 training samples. Extensive experiments on 14 state-of-the-art LLMs reveal that they struggle with dynamic code evolution, even with the support of advanced knowledge updating methods (e.g., DPO, ORPO, and SimPO). We believe that our benchmark can offer a strong foundation for the development of more effective methods for real-time code knowledge updating in the future. The experimental code and dataset are publicly available at: https://github.com/Lucky-voyage/Code-Sync.

Related papers

• GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities [26.381134558374743]
  We introduce GitChameleon 2.0, a novel, meticulously curated dataset comprising 328 Python code completion problems.<n>GitChameleon 2.0 rigorously evaluates the capacity of contemporary large language models (LLMs), LLM-powered agents, code assistants, and RAG systems to perform version-conditioned code generation.
  arXiv  Detail & Related papers  (2025-07-16T16:10:42Z)
• OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique [59.18475981916166]
  We introduce OpenCodeReasoning-II, a dataset consisting of 2.5M question-solution-critique triples (approx. 35K unique programming questions)<n>In this work, we employ a two-stage supervised fine-tuning strategy. The first stage focuses on fine-tuning for code generation, while the second stage involves the joint training of models for both code generation and critique. Notably, the integration of our code generation and critique models leads to significant improvements in competitive coding performance.
  arXiv  Detail & Related papers  (2025-07-11T23:35:54Z)
• ReCode: Updating Code API Knowledge with Reinforcement Learning [45.077641074621816]
  Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs.<n>We propose ReCode, a novel framework that mimics human programmer adaptation to API changes.<n>Our experiments demonstrate that ReCode substantially boosts LLMs' code generation performance in dynamic API scenarios.
  arXiv  Detail & Related papers  (2025-06-25T14:41:13Z)
• UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance [65.01483640267885]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge.<n>We introduce UnitCoder, a systematic pipeline leveraging model-generated unit tests to guide and validate the code generation process.<n>Our work presents a scalable approach that leverages model-generated unit tests to guide the synthesis of high-quality code data from pre-training corpora.
  arXiv  Detail & Related papers  (2025-02-17T05:37:02Z)
• DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models [36.266383541354294]
  This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them apart from traditional code generation tasks. Second, examples in DA-Code are all based on real and diverse data, covering a wide range of complex data wrangling and analytics tasks. Third, to solve the tasks, the models must utilize complex data science programming languages, to perform intricate data processing and derive the answers.
  arXiv  Detail & Related papers  (2024-10-09T18:00:05Z)
• CodeUpdateArena: Benchmarking Knowledge Editing on API Updates [77.81663273436375]
  We present CodeUpdateArena, a benchmark for knowledge editing in the code domain. An instance in our benchmark consists of a synthetic API function update paired with a program synthesis example. Our benchmark covers updates of various types to 54 functions from seven diverse Python packages.
  arXiv  Detail & Related papers  (2024-07-08T17:55:04Z)
• VersiCode: Towards Version-controllable Code Generation [58.82709231906735]
  Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development. We propose two novel tasks aimed at bridging this gap: version-specific code completion (VSCC) and version-aware code migration (VACM) We conduct an extensive evaluation on VersiCode, which reveals that version-controllable code generation is indeed a significant challenge.
  arXiv  Detail & Related papers  (2024-06-11T16:15:06Z)
• EVOR: Evolving Retrieval for Code Generation [17.46870626157077]
  Existing pipelines for retrieval-augmented code generation employ static knowledge bases with a single source. We develop a novel pipeline, EVOR, that employs the synchronous evolution of both queries and diverse knowledge bases.
  arXiv  Detail & Related papers  (2024-02-19T17:37:28Z)
• CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code [6.491009626125319]
  We introduce CodeLL, a lifelong learning dataset focused on code changes. Our dataset aims to comprehensively capture code changes across the entire release history of open-source software repositories. CodeLL enables researchers studying the behaviour of LMs in lifelong fine-tuning settings for learning code changes.
  arXiv  Detail & Related papers  (2023-12-20T01:20:24Z)
• Exploring Continual Learning for Code Generation Models [80.78036093054855]
  Continual Learning (CL) is an important aspect that remains underexplored in the code domain. We introduce a benchmark called CodeTask-CL that covers a wide range of tasks, including code generation, translation, summarization, and refinement. We find that effective methods like Prompt Pooling (PP) suffer from catastrophic forgetting due to the unstable training of the prompt selection mechanism.
  arXiv  Detail & Related papers  (2023-07-05T16:58:39Z)
• ReACC: A Retrieval-Augmented Code Completion Framework [53.49707123661763]
  We propose a retrieval-augmented code completion framework, leveraging both lexical copying and referring to code with similar semantics by retrieval. We evaluate our approach in the code completion task in Python and Java programming languages, achieving a state-of-the-art performance on CodeXGLUE benchmark.
  arXiv  Detail & Related papers  (2022-03-15T08:25:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.