TEPA: Revoking Stale Memories for Conflict-Robust Language Agents· TEPA：撤销过时记忆以增强语言代理的冲突鲁棒性
Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, stale memories can remain retrievable and pollute the prompt. We characterize this failure mode as memory pollution: degradation caused by active memories that newer conflicting evidence has superseded. We introduce TEPA, a revocable evidence-memory mechanism that makes validity an explicit state of memory. TEPA represents observations as keyed precedents and revokes active precedents when fresh evidence contradicts them under the same key, allowing retrieval to draw from current evidence while preserving revoked history for audit. Across controlled hidden-regime drift, real file-backed executable drift, and prefe
通过撤销过时记忆，增强语言代理处理冲突信息的能力。
- 核心方法
- TEPA机制通过为每个观察赋予键，并在新证据下撤销相同键的旧记忆，显式管理记忆的有效性状态。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 长期记忆可能会导致过时信息与新信息冲突，从而污染语言代理的输出。
- 关键实验
- 实验涵盖了受控的隐含体制漂移、真实的文件支持执行漂移和偏好变化场景，展示了TEPA的有效性。
- 主要贡献
- 提出了一种新的记忆管理机制，有效减少了因过时记忆导致的输出污染，提高语言代理的鲁棒性和可审计性。
- 意义与局限
- 该研究提高了语言代理处理动态环境的能力，但可能在高频率信息更新的场景下效率受限。