TARL：面向长期智能体可执行内存管理的事务感知可靠账本
TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents
浏览论文内容
中文总结 AI 辅助
本文针对长期智能体持久内存更新易出错的问题，提出事务感知可靠账本框架TARL，搭配基准TARL-Mem，在多类评估中提升了内存管理的多项关键指标。
中文摘要 AI 辅助
持久内存可帮助长期智能体保留知识，但单次更新错误会反复干扰后续的检索与推理。现有多数系统将内存更新简化为二元的写入/保留决策，无法区分新信息应被添加、忽略、用于修正过时信念、因不可靠被拒绝，还是需推迟验证；这些选择可能共享同一二元标签，却会产生完全不同的内存状态。本文提出TARL，一种内存状态更新框架，将每条语句映射至五种可执行操作之一：TARL会识别受影响的内存、确定其时间范围、比较源可靠性，并更新已接受、待处理及已拒绝的账本；该框架通过对比不同更新操作产生的内存状态进行训练，以促使模型选择能导向正确结果的操作。本文还推出TARL-Mem，一个带有细粒度操作标签和下一状态目标的基准。在域内、跨源、时间、反事实及序列评估中，TARL提升了操作预测与状态恢复能力，减少了内存污染，保留了冲突证据，并限制了累积损坏。完整模型实现见补充材料。
英文摘要
Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems reduce memory updating to a binary Write/Hold decision, which cannot distinguish whether new information should be added, ignored, used to revise an outdated belief, rejected as unreliable, or deferred for verification. These choices may share the same binary label while producing fundamentally different memory states. We introduce TARL, a memory state update framework that maps each statement to one of five executable actions. TARL identifies the affected memory, resolves its temporal scope, compares source reliability, and updates accepted, pending, and rejected ledgers. It is further trained by comparing the memory states produced by alternative update operations, encouraging the model to select the operation that leads to the correct result. We also introduce TARL-Mem, a benchmark with fine-grained action labels and next-state targets. Across in-domain, cross-source, temporal, counterfactual, and sequential evaluations, TARL improves action prediction and state recovery, reduces memory pollution, preserves conflicting evidence, and limits cumulative corruption.
