用自问自答链提升大模型编程质量，减少遗漏与设计缺陷。
Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain
- 将用户目标分解为步骤并自动生成逐层提问验证约束。
- 在接口设计等复杂领域，大模型质量评分提升12%~28%。
- 适合关注代码质量、安全性和模块化的开发研究者。
大语言模型加速了AI辅助软件开发，但实际应用仍受限于实现不完整、模块化差和安全实践不一致等问题。本文提出Questions-of-Thoughts（QoT），一种质量驱动的推理时框架，将用户目标转化为有序工程步骤与分步自问机制，以验证约束、减少遗漏错误，同时保持轻量推理记录，稳定后续设计决策。我们在三个典型后端领域（API设计、数据通信、文件系统）评估QoT，每项任务需多模块拆解，并暴露典型生成系统故障模式。采用受ISO/IEC启发的质量评分标准，衡量可扩展性、完整性、模块化和安全性。结果表明：在更大模型和更复杂领域中，QoT带来显著质量提升，总质量得分提高12%~28%；小模型在上下文和规划预算紧张时可能产生权衡。我们开源了提示、评分指南、原始生成物及复现脚本，支持应用AI与数据分析研究。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) have accelerated AI-assisted software development, yet practical deployment remains constrained by incomplete implementations, weak modularization, and inconsistent security practices. We introduce Questions-of-Thoughts (QoT), a quality-driven inference-time scaffold that turns a user goal into (i) an ordered sequence of engineering steps and (ii) stepwise self-questioning to verify constraints and reduce omission errors, while maintaining a lightweight reasoning record that stabilizes subsequent design decisions. We evaluate QoT across three representative backend engineering domains: API Design, Data Communication, and File Systems. Each task requires multi-module decomposition and exposes standard failure modes in LLM-generated systems. To enable data-driven comparison, we score generated artifacts using an ISO/IEC-inspired quality rubric that measures Scalability, Completeness, Modularity, and Security. We report domain-wise gains as the change in total quality score, defined as the QoT score minus the NoQoT score. Results show capacity-dependent improvements: QoT yields consistent quality improvements for larger models and more complex domains, while smaller models may exhibit trade-offs under tight context and planning budgets. We release an open artifact with prompts, scoring guidelines, raw generations, and scripts that reproduce the reported tables and figures to support applied AI and data analytics research.
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。