AI 中文总结
针对可变RAG中历史冲突导致的语义遮蔽与状态发散问题，提出GC-Mem推理时一致性协议，利用时间支配算子和矛盾检测精准清除遮蔽上下文，在13.7万记忆块基准上恢复超90%冲突解决准确率。
AI 中文摘要
检索增强生成（RAG）作为长时程自主智能体的主要记忆架构。然而，将共享记忆视为仅追加的流会引入\textit{语义遮蔽}，这是一种关键故障模式，其中冲突的历史观察不断累积并在统计上主导有效的最新更新。在动态环境中，这会导致严重的状态发散，因为智能体检索并依据过时事实行动。本文形式化了状态可变性的机制，以证明标准稠密检索存在渐近召回衰减。此外，我们形式化地展示了多数投票陷阱，揭示增加检索上下文窗口会因语义等价条件下稀释注意力机制而矛盾地降低生成准确性。为解决此问题，我们引入了GC-Mem（记忆垃圾回收），一种严格的推理时一致性协议。与启发式时间衰减机制（其不加区分地破坏有效长期记忆）不同，GC-Mem纯粹依赖时间支配算子（$\Phi_{\mathcal{T}}$）结合矛盾检测，以精准切除被遮蔽的上下文。在包含137,760个记忆块和连续累积扫描的严格、行为推断基准上评估，标准RAG和时间戳重排序基线经历严重退化。相比之下，GC-Mem经验性地恢复了超过90%的冲突解决准确性。我们建立了精确的精度和召回部署阈值，确保在标准可变RAG根本失败的情况下实现状态收敛。
英文摘要
Retrieval-Augmented Generation (RAG) serves as the primary memory architecture for long-horizon autonomous agents. However, treating shared memory as an append-only stream introduces \textit{Semantic Shadowing}, a critical failure mode where conflicting historical observations accumulate and statistically dominate valid recent updates. In dynamic environments, this results in severe state divergence as agents retrieve and act upon obsolete facts. This paper formalizes the mechanics of State Mutability to prove that standard dense retrieval suffers from Asymptotic Recall Decay. Furthermore, we formally demonstrate a Majority Vote Trap, revealing that increasing the retrieval context window paradoxically degrades generation accuracy by diluting the attention mechanism under conditions of semantic equivalence. To resolve this, we introduce GC-Mem (Garbage Collection for Memory), a strict inference-time consistency protocol. Unlike heuristic time-decay mechanisms---which indiscriminately destroy valid long-term memory---GC-Mem relies purely on a temporal dominance operator ($Φ_{\mathcal{T}}$) paired with contradiction detection to surgically excise shadowed context. Evaluated across a rigorous, behaviorally inferred benchmark of 137,760 memory chunks and continuous accumulation sweeps, standard RAG and timestamp re-ranking baselines experience severe degradation. In contrast, GC-Mem empirically recovers $>90\%$ conflict resolution accuracy. We establish strict precision and recall deployment thresholds, ensuring state convergence where standard mutable RAG fundamentally fails.
