发表机构
Peking University; Legendspace Intelligence Technology Co., Ltd.; AI for Science Institute (AISI)（北京大学; 蓝箭航天空间科技股份有限公司; 科学智能研究院（AISI））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RocketAgent是一个长期工程智能体，通过单一编码智能体协调多学科设计，利用知识图谱和类型化设计中间表示管理依赖，并通过修订感知检查实现失效与阻止，在代表性案例中成功完成从冷却搜索到配置选择的全流程。
AI 中文摘要
液体火箭推力室设计涉及相互依赖的分析，其中下游约束可能要求重新审视早期的设计决策。在异构工具之间管理这些依赖关系需要在整个工作流程中保持一致的设计信息和协调的更新。我们提出了RocketAgent，一个用于液体火箭推力室多学科初步设计的长期工程智能体。一个拥有计划的单一编码智能体协调性能尺寸确定、子系统优化、几何生成和多物理场评估等工程技能。一个具有来源感知的知识图谱支持方法选择，而一个类型化的设计中间表示维护共享参数、工件和决策。具有修订感知的检查会使受影响的结果失效并阻止被取代的输入，其中重大变更需经工程审批。在一个具有代表性的基于仿真的设计中，RocketAgent从不可行的冷却搜索继续，经过工程师授权的操作点修订，识别出可行的子系统设计，并协调后续的几何生成和多物理场评估以支持最终配置选择。单独模块测试评估了代理预测和喷嘴适配。在三个受控场景中的双配置比较验证了在求解器执行前预期的依赖失效和被取代输入阻止。代表性案例展示了跨多学科设计工作流程的持续协调，而受控测试确立了支持该执行的修订机制的行为。
英文摘要
Liquid-rocket thrust-chamber design involves interdependent analyses in which downstream constraints can require earlier design decisions to be revisited. Managing these dependencies across heterogeneous tools requires consistent design information and coordinated updates throughout the workflow. We present RocketAgent, a long-horizon engineering agent for multidisciplinary preliminary design of liquid-rocket thrust chambers. A single plan-owning Coding Agent coordinates engineering skills for performance sizing, subsystem optimization, geometry generation, and multiphysics assessment. A provenance-aware knowledge graph supports method selection, while a typed Design Intermediate Representation maintains shared parameters, artifacts, and decisions. Revision-aware checks invalidate affected results and block superseded inputs, with consequential changes subject to engineering approval. In a representative simulation-based design, RocketAgent continued from an infeasible cooling search through an engineer-authorized operating-point revision, identified feasible subsystem designs, and coordinated subsequent geometry generation and multiphysics assessment to support final configuration selection. Separate module tests assessed surrogate predictions and nozzle adaptation. A two-configuration comparison across three controlled scenarios verified the expected dependency invalidations and superseded-input blocking before solver execution. The representative case demonstrates sustained coordination across a multidisciplinary design workflow, while the controlled tests establish the behavior of the revision mechanisms supporting that execution.
