建筑即仓库：KIR，一种用于智能体撰写的建筑信息模型的类型化中间表示
A Building as a Repository: KIR, a Typed Intermediate Representation for Agent-Authored Building Information Models
浏览论文内容
中文总结 AI 辅助
针对智能体撰写建筑信息模型时的静默错误，提出类型化中间表示KIR，以七种数据表示覆盖模糊、默认、义务等，实验验证其诊断能力与紧凑性。
中文摘要 AI 辅助
自主撰写建筑信息模型的智能体不仅需要访问宿主API，还需要一种表示，以记录其意图、编译器代表其做出的决定、被拒绝的内容、执行后观察到的结果以及仍未知的信息。我们提出KIR，一种类型化中间表示，其中建筑作为程序被撰写并保存在版本化仓库中，并作为构建目标降级到宿主应用。KIR围绕生成器在写入有状态、部分可观测宿主时可能静默出错的七种方式组织，并为每种方式提供数据表示：模糊选择器变为带候选的类型化拒绝；默认值保留其来源；不会被检查的义务在执行前被命名；空泛见证被静态拒绝；丢失的事务响应变为状态UNCONFIRMED并附带先验证后重试规则；反向路径遵循普查不变量；决策通过摘要绑定到其做出时所依据的状态。在包含83个操作契约且仅以Revit为后端的固定快照上，离线实验拒绝了42个压力测试程序中的29个，并给出诊断代码且无未捕获异常，将377个见证义务中的38个命名为不可见证，在七条既定不变量下接纳了100个执行、见证和接受状态组合中的31个，并在219次证书运行中未发现空泛见证；一座60层塔楼作为KIR为11,263字符，而生成的C#为3,709,235字符。原生Revit运行结果来自项目记录并单独报告，与复现结果分开。与直接编写宿主代码的智能体进行受控比较已制定但尚未执行；这是主要待解问题。
英文摘要
Autonomous agents that author building information models need more than access to a host API. They need a representation of what they intended, what a compiler decided on their behalf, what was refused, what was observed after execution and what remains unknown. We present KIR, a typed intermediate representation in which a building is authored as a program held in a versioned repository and lowered to host applications as build targets. KIR is organised around seven ways in which a generator writing into a stateful, partially observable host goes silently wrong, and gives each a representation in data: ambiguous selectors become typed refusals with candidates; defaults keep their provenance; obligations that will not be checked are named before execution; vacuous witnesses are rejected statically; a lost transaction response becomes the state UNCONFIRMED with a verify-before-retry rule; the reverse path obeys a census invariant; and decisions are bound by digest to the state they were made against. On a pinned snapshot with 83 operation contracts and Revit as the only backend, offline experiments refuse 29 of 42 stress-test programs with diagnostic codes and no uncaught exception, name 38 of 377 witness obligations as unwitnessable, admit 31 of 100 combinations of execution, witness and acceptance states under seven stated invariants, and find no vacuous witness in 219 certificate runs; a 60-storey tower is 11,263 characters as KIR against 3,709,235 characters of emitted C#. Native Revit runs are reported from project records and kept separate from reproduced results. A controlled comparison with agents that write host code directly is specified but not yet executed; it is the principal open question.
