RAC:面向约束管控工程任务的关系智能体契约
RAC: A Relational Agent Contract for Constraint-Governed Engineering Tasks
AI总结:
本文提出RAC契约,通过让智能体保留语义控制并委托工具推导机械结果,在PCB、调度等任务中提升了约束管控工程任务的制品可靠性,实现了更高的通过率。
摘要:
工程智能体必须生成满足精确耦合约束的制品,现有方案常要求智能体做出语义决策并从这些决策中推导精确几何或时序等结果,导致约束管控工程任务中出现失败。本文提出RAC,一种与工具无关的工程智能体动作与反馈层契约,它规定了权威观测、语义动作、基于工具的实现、独立验证及修复证据。智能体决定制品应满足的关系,专用工具推导其具体结果。在PCB布局、布线与修复任务中,RAC在所有9个评估模型中实现最高的一次通过率,平均为90.9%,而最强基线(仅需求委托)为74.0%;在车间调度中,直接关系动作的质量通过率达96.3%,而使用相同调度后端的代码介导交付为59.6%。我们对4种微控制器上的141个嵌入式代码任务的评估表明,动作契约是智能体能力的来源:在委托机械可推导输出的同时保留语义控制,可提升约束制品的可靠性。
英文摘要:
Engineering agents must produce artifacts that satisfy exact, coupled constraints. Existing solutions often require agents to make semantic decisions and also derive consequences such as precise geometry or timing from those decisions, leading to failures in constraint-governed engineering tasks. In this paper, we introduce RAC, a harness-agnostic contract for the action and feedback layer of engineering agents. It specifies authoritative observations, semantic actions, tool-based realization, independent verification, and repair evidence. The agent decides which relations an artifact should satisfy; specialized tools derive their concrete consequences. On PCB placement, routing, and repair tasks, RAC achieves the highest clean-pass rate for all nine evaluated models, averaging 90.9%, compared with 74.0% for the strongest baseline, requirements-only delegation. In job-shop scheduling, direct relational actions achieve 96.3% quality pass versus 59.6% for code-mediated delivery with access to the same scheduling backend. Our evaluations on 141 embedded-code tasks across four microcontroller identify the action contract as a source of agent capability: preserving semantic control while delegating mechanically derivable outputs improves the reliability of constrained artifacts.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。