提出测试记忆巩固的评估协议，让语言模型更智能地保留重要经历。
EVAF: A Test-Retest Protocol for Selective Parametric Consolidation
- 用门控LoRA机制选择性地固化高价值、高意外性的经验。
- 在干扰后仍保持行为持久性，参数漂移和跨角色污染低。
- 适合研究长期语言代理与记忆机制的学者参考。
长时间运行的语言代理需要决定哪些经验应在工作上下文消失后留存。检索系统可重新插入过去文本，但无法证明经验已被模型自身行为所选择性内化。我们提出EVAF——一种基于回声-情感吸引场的门控LoRA固化机制，以及一个在受控干扰下测量选择性参数固化的测试-重测协议。在GPT-2和TinyLlama上，EVAF优先固化高情感价值、高意外性的经验，同时通过互补路由记忆路径保持可检索的事实记忆。测试-重测结果表明，其在干扰后的行为持久性优于冻结、仅检索和无门控持续更新基线，且参数漂移与跨角色污染均较低。结果支持记忆访问与记忆深度的分离：检索事实与内化经验是两种不同的计算操作。
原文摘要 · Abstract (English)
Long-running language agents need mechanisms for deciding which experiences should persist after the working context is gone. Retrieval systems can reinsert past text, but they do not by themselves show that an experience has been selectively consolidated into the model's own behavior. We introduce EVAF, an Echo-Valence Attractor Field mechanism for gated LoRA consolidation, and a test-retest protocol for measuring selective parametric consolidation under controlled interference. Across GPT-2 and TinyLlama, EVAF preferentially consolidates high-valence, high-surprise experiences while preserving retrieval-accessible factual memory through a complementary routed memory path. Test-retest measurements show stronger post-interference behavioral persistence than frozen, retrieval-only, and ungated continual-update baselines, while keeping parameter drift and cross-persona contamination low. The results support a separation between memory access and memory depth: retrieving a fact and internalizing an experience are distinct computational operations.
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。