用几何方法提升对话记忆，让低配设备也能持久记住对话内容。
CoreMem: Riemannian Retrieval and Fisher-Guided Distillation for Long-Term Memory in Dialogue Agents
- 用黎曼几何替代传统相似度计算，避免记忆混乱问题。
- 在8GB显存下实现跨会话记忆，开放域和时序推理提升超4个百分点。
- 适合资源受限的边缘设备部署，尤其需要长期记忆的对话系统。
个性化对话代理需持续维护长期记忆以保证多轮交互连贯性。然而，在消费级硬件（如8GB VRAM边缘设备）上部署此类能力面临严重内存与计算瓶颈。现有系统通常依赖各向同性余弦相似度进行检索，并采用启发式规则压缩上下文，缺乏统一理论基础，常出现高维检索中的“中心点问题”及压缩过程中的语法碎片化。为此，我们提出CoreMem，一种基于信息几何统一建模的资源高效边缘-云记忆架构。首先，黎曼检索用局部自适应的Fisher-Rao度量取代余弦匹配，通过马哈拉诺比斯距离惩罚中心记忆，并结合O(Ndr) Woodbury加速实现实时搜索。其次，Fisher引导的离散令牌蒸馏（FDTD）引入层次化句到令牌压缩机制，从费雪信息迹推导敏感度评分，提供可解释的压缩-KL权衡，并显式保护结构语法。在LOCOMO和LongMemEval-S基准测试中，CoreMem显著提升准确率，开放域推理提升4.51个百分点，时序推理提升4.17个百分点。大量性能分析表明，CoreMem严格控制在8GB VRAM预算内，成功弥合资源受限边缘设备与理论严谨的终身记忆代理之间的差距。
原文摘要 · Abstract (English)
Personalized dialogue agents require continuous long-term memory to maintain coherent interactions across multiple sessions. However, deploying these capabilities on consumer-grade hardware (e.g., 8 GB VRAM edge devices) introduces severe memory and compute bottlenecks. Existing systems typically rely on isotropic cosine similarity for retrieval and heuristic rules for context compression. These approaches lack a unified theoretical foundation, frequently suffering from the hubness problem in high-dimensional retrieval and syntactic fragmentation during compression. To overcome these limitations, we propose CoreMem, a resource-efficient edge-cloud memory architecture fundamentally unified by information geometry. First, Riemannian retrieval replaces cosine matching with a locally adaptive Fisher-Rao metric, effectively penalizing hub memories via Mahalanobis distance with O(Ndr) Woodbury acceleration for real-time search. Second, Fisher-guided discrete token distillation (FDTD) introduces a hierarchical sentence-to-token compression mechanism. It derives sensitivity scores from Fisher information traces, providing a principled compression-KL tradeoff augmented with explicit structural syntax protection. Evaluated on the LOCOMO and LongMemEval-S benchmarks, CoreMem achieves strong accuracy improvements, yielding substantial gains in Open-domain (+4.51 pp) and Temporal (+4.17 pp) reasoning. Extensive profiling confirms that CoreMem operates seamlessly within a strict 8 GB VRAM budget, successfully bridging the gap between resource-constrained edge devices and the demand for theoretically grounded, lifelong memory agents.
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。