让AI能主动遗忘过时知识，避免错误决策。
Towards Reversible Forgetting: Managing Obsolete Knowledge in Continual Enterprise AI Agents
- 设计三种记忆状态：活跃、休眠、退役，支持知识重启。
- 通过影子测试验证知识重激活，防止误删有用信息。
- 适合需持续更新的金融等企业级AI系统使用。
持续学习传统上将遗忘视为失败，强调在环境演化中保留已有知识。但我们认为，对于在非平稳环境中运行的企业AI代理而言，这一目标不完整——客户、政策、工具、工作流程、法规和市场条件随时间变化。无差别保留可能使过时知识影响决策，导致负迁移和运营风险。因此我们提出可逆遗忘：一种包含三种操作记忆状态（活跃、休眠、退役）的概念框架，并引入可重激活机制，在知识再次相关时恢复其可用性。我们实现该框架为具有滞后特性的可逆记忆控制器，累积相关性证据，采用不对称阈值防止状态振荡，通过影子模式测试重激活，并由策略控制退役。该框架在不混淆临时抑制与永久删除的前提下，降低过时信息的影响。以金融为例：某种市场环境下有效的知识可能在新环境下有害，但当相似条件重现时又可恢复价值。
原文摘要 · Abstract (English)
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. 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. 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. Finance illustrates the idea: knowledge useful under one market regime may become harmful under another yet regain relevance when similar conditions recur.
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。