Towards Reversible Forgetting: Managing Obsolete Knowledge in Continual Enterprise AI Agents

面向可逆遗忘：管理持续性企业 AI 智能体中的过时知识

Abstract: Continual learning has traditionally treated forgetting as a failure, emphasizing preservation of previously acquired knowledge as environments evolve. We argue that this objective is incomplete for enterprise AI agents operating in non-stationary environments, where customers, policies, tools, workflows, regulations, and market conditions change over time.

摘要： 持续学习传统上将“遗忘”视为一种失败，强调在环境演变过程中保留先前获取的知识。我们认为，对于在非平稳环境中运行的企业 AI 智能体而言，这一目标是不完整的，因为客户、政策、工具、工作流程、法规和市场条件会随时间推移而发生变化。

Indiscriminate retention can allow obsolete knowledge to influence decisions, creating negative transfer and operational risk. We therefore propose reversible forgetting: a conceptual framework with three operational memory states: active, dormant, and retired, and a reactivation transition that can restore dormant knowledge when its relevance returns.

不加区分的保留可能会导致过时知识影响决策，从而产生负迁移和运营风险。因此，我们提出了“可逆遗忘”：一个包含三种操作内存状态（活跃、休眠和退役）的概念框架，以及一种当知识相关性回归时可以恢复休眠知识的“再激活”转换机制。

We instantiate the framework as a Hysteretic Reversible Memory Controller that accumulates relevance evidence, uses asymmetric thresholds to prevent state oscillation, tests reactivation in shadow mode, and gates retirement through policy. The framework reduces the influence of obsolete information without conflating temporary suppression with permanent erasure.

我们将该框架实例化为一个“滞后可逆内存控制器”（Hysteretic Reversible Memory Controller），它通过积累相关性证据、使用非对称阈值来防止状态震荡、在影子模式下测试再激活，并通过策略来控制退役。该框架在减少过时信息影响的同时，不会将暂时的抑制与永久的删除混为一谈。

Finance illustrates the idea: knowledge useful under one market regime may become harmful under another yet regain relevance when similar conditions recur.

金融领域很好地阐释了这一理念：在某种市场机制下有用的知识，在另一种机制下可能变得有害，但当类似条件再次出现时，这些知识又会重新获得相关性。