激活引导的图检索：面向语言模型系统认知记忆重构的架构规范
Activation-Guided Graph Retrieval for Cognitive Memory Reconstruction in Language Model Systems
AI 导读
arXiv 一篇架构与分析类预印本提出，长期运行的 AI 系统除按查询相关性检索外，还需“激活条件化的记忆可用性”操作符。该架构由请求与目标线索种子化授权记忆图，用激活与扇出衰减分配有界遍历前沿，检索实体递归发出线索，在生成前重构类型化证据图。论文给出实现级成本估算、消融与失败条件及可复现评测协议，但未报告任何 benchmark 测量结果。
正文 · 原文
Abstract:Retrieval-augmented language model systems generally select context by query-conditioned relevance. We argue that long-lived AI systems require a second operator: activation-conditioned memory availability. We specify an architecture in which request and goal cues seed an authorized memory graph, activation and fan attenuation allocate a bounded traversal frontier, retrieved entities recursively emit cues, and a typed evidence graph is reconstructed before generation. The specification yields five architectural consequences about candidate selection, traversal control, graph regularization, evidence reconstruction, and reinforcement. We derive implementation-level cost estimates and define ablations, failure conditions, and a reproducible evaluation protocol. The central claim is narrowed or falsified if a simpler graph reranker matches full traversal on causal and temporal recovery under equal budgets. This architecture-and-analysis preprint reports no benchmark measurements. If the claim holds, retrieval returns the evidence path that makes a memory available, not only a ranked list.
| Comments: | Architecture and analysis preprint; no benchmark measurements. Companion research essay and revision notes: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| ACM classes: | H.3.3; I.2.4; I.2.11 |
| Cite as: | arXiv:2611.13127 [cs.AI] |
| (or arXiv:2611.13127v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13127 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Marvin Danig [view email]
[v1]
Mon, 9 Nov 2026 19:13:16 UTC (12 KB)
来源：arXiv cs.AI · arxiv.org