提出双循环诊断协议，让大模型记忆系统错误可定位、可验证、可迭代。
D$^2$ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory
- 设计双循环诊断框架，通过证据比对与追踪定位记忆各阶段故障
- 在三个基准上达到93.59%至57.20%准确率，关键模块提升超3个百分点
- 适合需要可解释、可调试记忆系统的研究者与工程团队
记忆是大模型智能体的核心能力。持久化记忆跨越会话实现回忆、修改与个性化，但其多阶段流程（摄入、检索、过滤、生成）导致故障难以定位：端到端评估仅知出错，不知具体环节。现有评估常缺成对统计比较、粒度级非退化检查及阶段级诊断痕迹。本文提出D²ACCI（诊断驱动的基于产物的闭环可控迭代）协议，外层诊断门基于成对证据、受保护切片监控与可追溯性，决定是否启用、标记或拒绝记忆干预。引入DCR评分衡量失败是否可定位，以及可复用的D²ACCI-Eval用于门控重播。在MemStack中实例化并评估三个公开基准，分别取得LoCoMo 93.59%、LongMemEval 90.93%、PersonaMem-V2 57.20%准确率。五组成对消融显示，补充提取、会话记忆检索与遗忘防护带来显著增益（+1.9至+3.7个百分点，全部p ≤ 0.003）。相反，BM25/RRF被保留为监控特性标志——此差异在仅报告聚合指标时不可见。诊断审计表明，丰富痕迹使根因一致率远高于仅结果重标。诊断产物的DCR@3达98–100%，而结果日志为0%。结果证明，稳健记忆迭代需可追溯、统计可靠、回归感知的证据支持——这正是D²ACCI填补的空白。
原文摘要 · Abstract (English)
Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi-stage pipeline (ingestion, retrieval, filtering, generation) makes failures difficult to localize: end-to-end evaluation reveals that an error occurred, but not which stage caused it. Existing evaluations often report aggregate performance without paired statistical comparisons, slice-level non-regression checks, or stage-level diagnostic traces. We propose D$^2$ACCI (Diagnostic-Driven Artifact-based Closed-loop Controlled Iteration), a dual-loop protocol whose outer diagnostic gate promotes, feature-flags, or rejects memory interventions based on paired evidence, protected-slice monitoring, and trace-level localizability. We further introduce DCR, a graded observability metric that measures whether failures remain localizable, and D$^2$ACCI-Eval, a reusable artifact for gate replay. We instantiate the protocol in MemStack and evaluate on three public benchmarks, achieving 93.59% on LoCoMo, 90.93% on LongMemEval, and 57.20% on PersonaMem-V2. Five paired ablations show that supplement extraction, session-memory retrieval, and Forget Guard yield statistically significant gains (+1.9 to +3.7pp, all p $\le$ .003). In contrast, BM25/RRF is retained as a monitored feature flag---a distinction invisible to aggregate-only evaluation. A diagnostic audit shows enriched traces substantially improve root-cause agreement over result-only relabeling. Diagnostic artifacts reach 98--100% DCR@3 versus 0% for results-only logs. These results establish that robust memory-system iteration demands traceable, statistically grounded, and regression-aware evidence---exactly the gap D$^2$ACCI fills.
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。