为多智能体大模型系统设计受控共享内存，解决知识泄漏与冲突等关键问题。
Governed Shared Memory for Multi-Agent LLM Systems
- 提出作用域检索、时间覆盖、溯源追踪等四项系统级抽象机制
- 实现100%深度四层推导链的溯源重建，单跳延迟低于秒级
- 适合构建高可靠多智能体系统的研发人员参考
多智能体大模型环境需要可靠的共享知识管理机制。本文形式化了舰队内存问题，并识别出四种基础故障模式：未经授权的泄露、过时传播、矛盾持续存在和溯源崩溃。为此，定义了四项显式的系统级原语：作用域检索、时间覆盖、溯源追踪和策略治理的内存传播。这些原语在MemClaw——一个生产级多租户内存服务中实现，并通过ArgusFleet进行可复现测试，评估四个治理维度。研究不采用基准对比，而是衡量真实生产服务，强调现实架构洞察与负面结果。关键评估结果：溯源方面，成功重建100%深度四层推导链，每跳延迟低于秒级且身份正确；传播方面，在舰队内实现高可见性，跨舰队无泄露；强写模式下，写入可见延迟优化至单次搜索往返。生产架构问题发现：作用域强制不对称，子租户作用域在直接按ID获取代理凭证时被绕过（研究期间披露并修复）；流水线顺序冲突，同步近似重复门会提前拒绝矛盾写入，导致异步矛盾检测器无法评估。结论：仅靠长上下文检索不足以支撑生产级多智能体内存。受控共享内存需显式系统级抽象，且真实运行评估对暴露执行与流水线顺序缺陷至关重要。
原文摘要 · Abstract (English)
Multi-agent LLM environments require robust mechanisms for shared knowledge management. This paper formalizes the fleet-memory problem and identifies four foundational failure modes: unauthorized leakage, stale propagation, contradiction persistence, and provenance collapse. To address these, we define explicit systems-level primitives: scoped retrieval, temporal supersession, provenance tracking, and policy-governed memory propagation. These primitives are implemented in MemClaw, a production multi-tenant memory service, and evaluated via ArgusFleet, a reproducible harness testing four governance dimensions. Rather than a baseline comparison, this study measures a live production service, emphasizing real-world architectural insights and negative results. Key Evaluation Results Provenance: Successfully reconstructed 100% of depth-four derivation chains with correct writer identity at sub-second per-hop latency. Propagation: Demonstrated high intra-fleet visibility with zero cross-fleet leakage. Under strong write mode, write-to-visible latency was optimized to a single search round-trip. Production Architectural Issues Discovered Asymmetric Scope Enforcement: Tenant isolation held, but sub-tenant scope was initially bypassed on direct GET-by-id requests for agent-scoped credentials (disclosed and remediated during the study). Pipeline Ordering Conflict: While contradiction supersession works for admitted writes, a synchronous near-duplicate gate can prematurely reject contradictory writes before the asynchronous contradiction detector can evaluate them. Conclusion: Long-context retrieval alone is insufficient for production multi-agent memory. Governed shared memory demands explicit systems-level abstractions, and live evaluation is vital to expose enforcement and pipeline-ordering failures missed by design-only treatments.
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。