让智能体更新知识时不改变身份，实现安全可靠的长期学习。
Episodic-to-Semantic Consolidation Without Identity Drift
- 将记忆整合为无身份变化的确定性函数，输出可查询的语义知识层。
- 实验显示规划失败尝试减少79.82%，身份在多次整合后仍字节相等。
- 适合需长期运行且身份不可变的自动化服务类智能体系统。
长期运行的自适应智能体面临知识固化与信息完整性的结构性矛盾。传统方法将知识固化视为模型变更：微调模型、重写提示、提炼策略或在上下文中附加反思，这些都会影响智能体的行为。但在受监管的自主部署中，这会带来风险，因为智能体需遵守绑定特定加密认证身份的承诺与审计合同。本文提出将知识固化视为一个确定性函数 f: M^ep → M^sem，作用于情景记忆，输出独立可访问的语义知识层；身份哈希不读取该语义记忆，因此固化更新知识而不改变认证身份。我们给出了智能体表示的形式化定义，通过结构引理证明身份不变性，设计了可审计的确定性聚合算法，其输出为带有置信度和事件溯源的数据库行，并通过合成实验验证：各项指标正确，跨整合周期身份字节相等，相比校准后的贝叶斯收缩基线，平均减少79.82%的无效规划尝试（95% BCa 置信区间 [78.02%, 81.49%]，共10个种子）。该方案为自主智能体提供了一种知识更新规范，使经验以可查询事实形式积累，而身份始终保持字节一致，以具身服务智能体为应用案例。
原文摘要 · Abstract (English)
Long-running adaptive intelligent agents face a structural tension between knowledge consolidation and information integrity. Memory consolidation is conventionally treated as an agent-changing operation: a model is fine-tuned, a prompt rewritten, a policy distilled, or a reflection appended to the context that governs future behaviour. In regulated autonomic deployment this is a liability because the agent operates under commitments and audit contracts that bind to a specific, cryptographically certified identity. We propose to treat consolidation not as a mutation of the planner or the identity manifest, but as a deterministic function f: M^ep -> M^sem over episodic memory whose output is a separately addressable semantic knowledge layer; the identity hash does not read M^sem, so consolidation updates knowledge without changing the agent's certified identity. We give a formal account of the agent representation, prove identity invariance through a structural lemma on the manifest's hash-input set, specify a deterministic aggregation algorithm whose outputs are auditable database rows with explicit confidence and supporting-event provenance, and validate the construction with synthetic experiments demonstrating per-field correctness, byte-equal identity across consolidation passes, and a mean 79.82% reduction in unproductive planner attempts (95% BCa CI [78.02%, 81.49%] across 10 seeds) against a calibrated Bayesian-shrunk baseline. The construction is a knowledge-update discipline for autonomic agents in which lessons accumulate as queryable facts while the agent's certified identity remains byte-equal across its operational lifetime, with an embodied service agent as the running case study.
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。