让智能系统复制信念而非比特，提升分布式决策的灵活性与可靠性。
Replicating Belief, Not Bits: Epistemic State Replication for Agentic Systems
- 用证据日志与信念谱系分离状态，实现对认知状态的复制。
- 在公平交付下，语义分歧受控且最终趋于一致，减少错误传播。
- 适合依赖大模型的自治系统，如智能运维、自动化决策等场景。
在分布式系统中，传统状态机复制（SMR）假设正确副本通过确定性转换达到完全相同的比特状态。然而，随着自主、随机且由模型驱动的智能体协同基础设施的兴起，确定性的比特级复制已不再足够。使用生成模型的副本可能产生不同的推理路径、摘要和标记边界，但依然能达成语义等价且正确的操作决策。强制比特一致性会降低执行灵活性，引发上下文遗忘并限制性能。我们主张，在此类系统中副本应复制信念而非比特。提出信念状态复制（ESR）机制，将复制边界从数据可见性转移到知识可见性。形式化节点状态为一对K = (L, B)，分离不可变的证据日志（L）与动态演化的信念谱系（B）。定义语义线性化要求操作反映验证器约束下的最新可接受语义，以及有界最终一致性，确保在公平传递、单调证据、有限验证干扰及收缩嫁接算子条件下，预期语义偏差可控。设计基于结构化信念增量的传播协议，并形式化可验证语义回滚，以移除错误前提而不造成上下文遗忘。原型实现表明，在假设条件下可行，并显著减少二次认知错误。
原文摘要 · Abstract (English)
In distributed systems, the classical State Machine Replication (SMR) model assumes that correct replicas execute deterministic transitions to yield identical bitwise states. However, the rise of agentic distributed systems -- where autonomous, stochastic, and model-driven agents orchestrate infrastructure -- presents scenarios where deterministic, bitwise replication is insufficient. Replicas operating with generative models may exhibit divergent reasoning paths, summaries, and token boundaries, yet reach semantically equivalent and correct operational decisions. Forcing bitwise agreement across these stochastic participants degrades execution flexibility, induces context amnesia, and limits performance. We argue that in such settings replicas should agree on belief, not bits. We propose Epistemic State Replication (ESR), a belief-replication layer for agentic distributed systems that shifts the replication boundary from data visibility to knowledge visibility. We formalize the epistemic node state as a pair K = (L, B) separating the deterministic, immutable evidence log (L) from the stochastic, evolving belief lineage (B). To govern execution safety, we define Semantic Linearizability, which requires operations to reflect the latest committed operational meaning within a verifier-bounded semantic compatibility metric, and Bounded Eventual Coherence, which bounds expected semantic divergence under fair delivery, monotonic evidence, bounded verifier disturbance, and a contractive graft operator. We outline protocols for propagating derived insights using structured epistemic deltas, and formalize Verifiable Semantic Rollbacks to prune faulty premises from belief lineages without inducing context amnesia. We prototype ESR and report preliminary simulation results that show feasibility under the stated assumptions and illustrate reductions in secondary cognitive faults.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。