GateLens: 一种增强推理能力的LLM代理用于汽车软件发布分析
GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics
AI总结：
GateLens是一种基于LLM的代理，通过引入关系代数作为中间表示，提升复杂表格数据分析的效率与准确性，适用于汽车软件发布分析领域。
AI中文摘要：
确保可靠的数据驱动决策在那些分析准确性直接影响安全、合规或运营结果的领域至关重要。此类领域中的决策支持依赖于大规模的表格数据集，其中手动分析效率低下、成本高昂且容易出错。尽管大型语言模型（LLM）提供了有前景的自动化潜力，但它们在分析推理、结构化数据处理和歧义解决方面面临挑战。本文介绍了一个基于LLM的架构GateLens，用于可靠分析复杂的表格数据。其关键创新是使用关系代数（RA）作为自然语言推理和可执行代码之间的正式中间表示，解决直接生成方法中可能出现的推理到代码的差距。在我们的汽车实例中，GateLens将自然语言查询转换为RA表达式，并生成优化的Python代码。与传统多代理或基于规划的系统相比，GateLens强调速度、透明度和可靠性。我们验证了该架构在汽车软件发布分析中的有效性，实验结果表明，GateLens在真实世界数据集上优于现有的链式推理（CoT）+ 自我一致性（SC）系统，特别是在处理复杂和歧义查询方面。消融研究证实了RA层的关键作用。工业部署显示分析时间减少了超过80%，同时在特定领域任务中保持了高准确性。GateLens在零样本设置中运行有效，无需要求少量示例或代理协调。这项工作通过识别关键的架构特征——中间正式表示、执行效率和低配置开销，推动了可部署LLM系统的设计，这些特征对于特定领域的分析应用至关重要。
英文摘要：
Ensuring reliable data-driven decisions is crucial in domains where analytical accuracy directly impacts safety, compliance, or operational outcomes. Decision support in such domains relies on large tabular datasets, where manual analysis is slow, costly, and error-prone. While Large Language Models (LLMs) offer promising automation potential, they face challenges in analytical reasoning, structured data handling, and ambiguity resolution. This paper introduces GateLens, an LLM-based architecture for reliable analysis of complex tabular data. Its key innovation is the use of Relational Algebra (RA) as a formal intermediate representation between natural-language reasoning and executable code, addressing the reasoning-to-code gap that can arise in direct generation approaches. In our automotive instantiation, GateLens translates natural language queries into RA expressions and generates optimized Python code. Unlike traditional multi-agent or planning-based systems that can be slow, opaque, and costly to maintain, GateLens emphasizes speed, transparency, and reliability. We validate the architecture in automotive software release analytics, where experimental results show that GateLens outperforms the existing Chain-of-Thought (CoT) + Self-Consistency (SC) based system on real-world datasets, particularly in handling complex and ambiguous queries. Ablation studies confirm the essential role of the RA layer. Industrial deployment demonstrates over 80% reduction in analysis time while maintaining high accuracy across domain-specific tasks. GateLens operates effectively in zero-shot settings without requiring few-shot examples or agent orchestration. This work advances deployable LLM system design by identifying key architectural features--intermediate formal representations, execution efficiency, and low configuration overhead--crucial for domain-specific analytical applications.
