MemTxn：智能体记忆中源支持更新与完整状态恢复的事务边界
MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
AI总结：
针对大语言模型智能体持久内存错误问题，提出MemTxn治理层，通过Ordered PatchTest等组件实现可靠更新与恢复，在多个基准测试中性能优于现有方法。
AI中文摘要：
持久内存支持长期运行的大语言模型智能体在会话和任务间复用信息，但可写内存中的错误会持续存在并破坏后续行为。现有系统改进了存储与检索，却未提供可靠更新与恢复的事务边界。为此，我们提出MemTxn，这是一个位于答案模型之外的治理层。MemTxn会验证更新是否有其来源支持，在事实冲突时选择可见版本，并在故障后恢复应用可见状态。该系统使用Ordered PatchTest验证写入，Temporal Resolver选择版本，以及持久快照日志恢复状态。在项目不重叠的审计中，MemTxn接受全部60个受支持的原始项，拒绝全部179个硬负样本。在LongMemEval-S和LoCoMo状态下的持久多键故障中，它无需知晓实际物理写入集即可恢复完整的声明式活动映射。在MemoryAgentBench FactConsolidation任务中，MemTxn在全部12种答案模型配置下取得最高平均F1值，在5个代表性设置中性能优于Dense模型17.06至24.07个百分点。
英文摘要：
Persistent memory lets long-running large language model agents reuse information across sessions and tasks. Yet errors in writable memory can persist and corrupt future behavior. Existing systems improve storage and retrieval, but they do not provide a transaction boundary for reliable updates and recovery. We therefore propose MemTxn, a governance layer outside the answer model. MemTxn verifies whether an update is supported by its source. It also selects the visible version when facts conflict and restores the application-visible state after a fault. The system uses Ordered PatchTest to validate writes, a Temporal Resolver to select versions, and a durable snapshot journal to recover state. On an item-disjoint audit, MemTxn accepts all 60 supported originals and rejects all 179 hard negatives. Under persistent multi-key faults on LongMemEval-S and LoCoMo states, it restores the complete declared active map without knowing the actual physical write set. On MemoryAgentBench FactConsolidation, MemTxn achieves the highest average F1 across all twelve answer-model configurations. It outperforms Dense by 17.06--24.07 points in five representative settings.
