We deployed an LLM agent with ReAct reasoning and full data access. It executed flawlessly, yet when asked "Why is completion rate 80%?", it returned metrics instead of causal explanation. The agent knew how to reason but we had not specified what to reason about. This reflects a gap: runtime reasoning frameworks (ReAct, Chain-of-Thought) have transformed LLM agents, but design-time specification--determining what domain knowledge agents need--remains under-explored. We propose 4D-ARE (4-Dimensional Attribution-Driven Agent Requirements Engineering), a preliminary methodology for specifying attribution-driven agents. The core insight: decision-makers seek attribution, not answers. Attribution concerns organize into four dimensions (Results -> Process -> Support -> Long-term), motivated by Pearl's causal hierarchy. The framework operationalizes through five layers producing artifacts that compile directly to system prompts. We demonstrate the methodology through an industrial pilot deployment in financial services. 4D-ARE addresses what agents should reason about, complementing runtime frameworks that address how. We hypothesize systematic specification amplifies the power of these foundational advances. This paper presents a methodological proposal with preliminary industrial validation; rigorous empirical evaluation is planned for future work.

翻译：我们部署了一个具备ReAct推理能力和全数据访问权限的LLM智能体。其执行过程完美无误，然而当被问及“为何完成率为80%？”时，它返回的是度量指标而非因果解释。该智能体知晓如何进行推理，但我们并未明确指定其应推理的内容。这反映出一个关键缺口：运行时推理框架（如ReAct、思维链）已彻底改变了LLM智能体的能力，但设计时规范——即确定智能体需要何种领域知识——仍未得到充分探索。我们提出4D-ARE（四维归因驱动智能体需求工程），这是一种用于规范归因驱动智能体的初步方法论。其核心洞见在于：决策者寻求的是归因，而非答案。受Pearl因果层级理论启发，归因问题可系统性地组织为四个维度（结果→过程→支持→长期）。该框架通过五个层次进行可操作化，生成可直接编译为系统提示的产出物。我们通过在金融服务领域的工业试点部署展示了该方法论。4D-ARE解决了智能体“应推理什么”的问题，与解决“如何推理”的运行时框架形成互补。我们假设系统化的规范能放大这些基础性进展的效能。本文提出了具有初步工业验证的方法论方案，严格的实证评估计划在后续工作中展开。