解耦正确性与策略：多智能体系统的确定性因果结构 (Decoupling Correctness from Policy: A Deterministic Causal Structure for Multi-Agent Systems)

In distributed multi-agent systems, correctness is often entangled with operational policies such as scheduling, batching, or routing, which makes systems brittle since performance-driven policy evolution may break integrity guarantees. This paper introduces the Deterministic Causal Structure (DCS), a formal foundation that decouples correctness from policy. We develop a minimal axiomatic theory and prove four results: existence and uniqueness, policy-agnostic invariance, observational equivalence, and axiom minimality. These results show that DCS resolves causal ambiguities that value-centric convergence models such as CRDTs cannot address, and that removing any axiom collapses determinism into ambiguity. DCS thus emerges as a boundary principle of asynchronous computation, analogous to CAP and FLP: correctness is preserved only within the expressive power of a join-semilattice. All guarantees are established by axioms and proofs, with only minimal illustrative constructions included to aid intuition. This work establishes correctness as a fixed, policy-agnostic substrate, a Correctness-as-a-Chassis paradigm, on which distributed intelligent systems can be built modularly, safely, and evolvably.

翻译：在分布式多智能体系统中，正确性常与调度、批处理或路由等操作策略纠缠在一起，这导致系统脆弱，因为性能驱动的策略演进可能破坏完整性保证。本文提出确定性因果结构（DCS），作为一种将正确性与策略解耦的形式化基础。我们建立了一套最小化的公理理论，并证明了四个结果：存在性与唯一性、策略无关的不变性、观测等价性以及公理最小性。这些结果表明，DCS解决了以值为中心的收敛模型（如CRDT）无法处理的因果模糊性问题，且移除任一公理都会使确定性退化为模糊性。因此，DCS作为异步计算的一个边界原则出现，类似于CAP定理和FLP定理：正确性仅在并半格的表达能力范围内得以保持。所有保证均由公理和证明确立，仅包含最少的示例构造以辅助直观理解。本工作将正确性确立为一个固定、策略无关的底层基础，即“正确性即底盘”范式，使得分布式智能系统能够以模块化、安全且可演进的方式构建其上。