LLM Agents for Automated Dependency Upgrades

• URL: http://arxiv.org/abs/2510.03480v1
• Date: Fri, 03 Oct 2025 19:57:10 GMT
• Title: LLM Agents for Automated Dependency Upgrades
• Authors: Vali Tawosi, Salwa Alamir, Xiaomo Liu, Manuela Veloso,
• Abstract summary: We introduce a framework of LLM agents to automatically recommend and apply code updates and ensure compatibility with new versions.<n>Our solution can automatically localize updated library usages in live Javas and implement recommended fixes in a user-friendly manner.<n>Results show that our approach not only performs upgrades using fewer tokens but also achieves a precision of 71.4%, highlighting its efficiency and effectiveness compared to state-of-the-art methods.
• Score: 14.958375551367132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As a codebase expands over time, its library dependencies can become outdated and require updates to maintain innovation and security. However, updating a library can introduce breaking changes in the code, necessitating significant developer time for maintenance. To address this, we introduce a framework of LLM agents to be used in combination with migration documentation to automatically recommend and apply code updates and ensure compatibility with new versions. Our solution can automatically localize updated library usages in live Java codebases and implement recommended fixes in a user-friendly manner. The system architecture consists of multiple key components: a Summary Agent, Control Agent, and Code Agent. To validate our approach, we apply the framework on an industrial use case by which we create three synthetic code repositories with major Upgrade changes and benchmark our approach against state-of-the-art methods. Results show that our approach not only performs upgrades using fewer tokens across all cases but also achieves a precision of 71.4%, highlighting its efficiency and effectiveness compared to state-of-the-art methods.

Related papers

• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models [63.54707418559388]
  We propose patching for large language models (LLMs) like software versions.<n>Our method enables rapid remediation by prepending a compact, learnable prefix to an existing model.
  arXiv  Detail & Related papers  (2025-11-11T17:25:44Z)
• Code2MCP: Transforming Code Repositories into MCP Services [53.234097255779744]
  Model Context Protocol (MCP) aims to create a standard for how Large Language Models use tools.<n>We introduce Code2MCP, an agent-based framework that automatically transforms a GitHub repository into a functional MCP service.<n>We demonstrate that Code2MCP successfully transforms open-source computing libraries in scientific fields such as bioinformatics, mathematics, and fluid dynamics.
  arXiv  Detail & Related papers  (2025-09-07T06:13:25Z)
• AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications [95.42093979627703]
  AgentScope supports flexible and efficient tool-based agent-environment interactions.<n>We ground agent behaviors in the ReAct paradigm and offer advanced agent-level infrastructure.<n>AgentScope also includes robust engineering support for developer-friendly experiences.
  arXiv  Detail & Related papers  (2025-08-22T10:35:56Z)
• Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code [0.0]
  Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps.<n>We propose a novel context engineering workflow that combines multiple AI components: an Intent Translator (GPT-5) for clarifying user requirements, an Elicit-powered semantic literature retrieval for injecting domain knowledge, and a NotebookLM-based document synthesis for contextual understanding, and a Claude Code multi-agent system for code generation and validation.
  arXiv  Detail & Related papers  (2025-08-09T14:45:53Z)
• CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System [52.048087777953064]
  We propose CompileAgent, an agent framework dedicated to repo-level compilation.<n>CompileAgent integrates five tools and a flow-based agent strategy, enabling interaction with software artifacts for compilation instruction search and error resolution.<n>We show that our method significantly improves the compilation success rate, ranging from 10% to 71%.
  arXiv  Detail & Related papers  (2025-05-07T08:59:14Z)
• Autonomous Legacy Web Application Upgrades Using a Multi-Agent System [3.456157428615978]
  Large Language Models (LLMs) for autonomous code generation is gaining attention in emerging technologies.<n>Many outdated web applications pose security and reliability challenges, yet companies continue using them due to the complexity and cost of upgrades.<n>We propose an LLM-based multi-agent system that autonomously upgrades legacy web applications to the latest versions.
  arXiv  Detail & Related papers  (2025-01-31T15:14:14Z)
• ContextModule: Improving Code Completion via Repository-level Contextual Information [11.459065573651348]
  ContextModule improves the relevance and precision of generated code.<n>We implement performance optimizations, such as index caching, to ensure the system meets the latency constraints of real-world coding environments.
  arXiv  Detail & Related papers  (2024-12-11T03:15:49Z)
• Linking Code and Documentation Churn: Preliminary Analysis [2.033674689332928]
  This study investigates the synchrony between code churn and documentation updates in three GitHub open-source projects. Preliminary results indicate varying degrees of synchrony across projects, highlighting the importance of integrated concurrent documentation practices. The novelty of this study lies in demonstrating how synchronizing code changes with documentation updates can improve the development lifecycle by enhancing diversity and efficiency.
  arXiv  Detail & Related papers  (2024-10-08T12:41:58Z)
• CodeUpdateArena: Benchmarking Knowledge Editing on API Updates [77.81663273436375]
  We present CodeUpdateArena, a benchmark for knowledge editing in the code domain.<n>An instance in our benchmark consists of a synthetic API function update paired with a program synthesis example.<n>Our benchmark covers updates of various types to 54 functions from seven diverse Python packages.
  arXiv  Detail & Related papers  (2024-07-08T17:55:04Z)
• RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation [79.83270415843857]
  We introduce RepoAgent, a large language model powered open-source framework aimed at proactively generating, maintaining, and updating code documentation. We have validated the effectiveness of our approach, showing that RepoAgent excels in generating high-quality repository-level documentation.
  arXiv  Detail & Related papers  (2024-02-26T15:39:52Z)
• Automatically Recommend Code Updates: Are We There Yet? [14.997510035210842]
  We present the first evaluation of state-of-the-art CodeLMs for automatically recommending code updates. Our results reveal that while CodeLMs perform well in settings that ignore temporal information, they struggle in more realistic time-wise scenarios. Our findings highlight the significant gap between the perceived and actual effectiveness of CodeLMs for real-world code update recommendation.
  arXiv  Detail & Related papers  (2022-09-15T05:07:25Z)

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.