让大模型编程更可信：通过多代理协作增强代码可审计性
From Helpful to Trustworthy: LLM Agents for Pair Programming
- 用多代理系统将模糊需求转为规范要求和形式化规格
- 借助自动反馈（如反例）迭代优化测试与实现
- 支持重构、接口迁移等维护任务，保持行为一致性
基于大语言模型的编程代理正广泛用于生成代码、测试和文档，但其输出可能看似合理却偏离开发者意图，且缺乏可审查证据，难以在持续演进的项目中维持可靠性。本博士研究提出系统性方法，通过多代理协作外化开发意图，并结合开发工具进行迭代验证。研究包含三项内容：将非正式问题描述转化为符合标准的需求与形式化规格；利用自动化反馈（如求解器生成的反例）改进测试与实现；在保持已验证行为的前提下支持重构、API迁移和文档更新等维护任务。预期成果将明确多代理工作流提升信任的条件，并为构建真实开发场景中的可靠编程助手提供实践指导。
原文摘要 · Abstract (English)
LLM-based coding agents are increasingly used to generate code, tests, and documentation. Still, their outputs can be plausible yet misaligned with developer intent and provide limited evidence for review in evolving projects. This limits our understanding of how to structure LLM pair-programming workflows so that artifacts remain reliable, auditable, and maintainable over time. To address this gap, this doctoral research proposes a systematic study of multi-agent LLM pair programming that externalizes intent and uses development tools for iterative validation. The plan includes three studies: translating informal problem statements into standards aligned requirements and formal specifications; refining tests and implementations using automated feedback, such as solver-backed counterexamples; and supporting maintenance tasks, including refactoring, API migrations, and documentation updates, while preserving validated behavior. The expected outcome is a clearer understanding of when multi-agent workflows increase trust, along with practical guidance for building reliable programming assistants for real-world development.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。