MemoriesDB: A Temporal-Semantic-Relational Database for Long-Term Agent Memory / Modeling Experience as a Graph of Temporal-Semantic Surfaces

• URL: http://arxiv.org/abs/2511.06179v1
• Date: Sun, 09 Nov 2025 01:41:55 GMT
• Title: MemoriesDB: A Temporal-Semantic-Relational Database for Long-Term Agent Memory / Modeling Experience as a Graph of Temporal-Semantic Surfaces
• Abstract summary: We introduce MemoriesDB, a unified data architecture designed to avoid decoherence across time, meaning, and relation.<n>Each memory is a time-semantic-relational entity that simultaneously encodes when an event occurred, what it means, and how it connects to other events.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce MemoriesDB, a unified data architecture designed to avoid decoherence across time, meaning, and relation in long-term computational memory. Each memory is a time-semantic-relational entity-a structure that simultaneously encodes when an event occurred, what it means, and how it connects to other events. Built initially atop PostgreSQL with pgvector extensions, MemoriesDB combines the properties of a time-series datastore, a vector database, and a graph system within a single append-only schema. Each memory is represented as a vertex uniquely labeled by its microsecond timestamp and accompanied by low- and high-dimensional normalized embeddings that capture semantic context. Directed edges between memories form labeled relations with per-edge metadata, enabling multiple contextual links between the same vertices. Together these constructs form a time-indexed stack of temporal-semantic surfaces, where edges project as directional arrows in a 1+1-dimensional similarity field, tracing the evolution of meaning through time while maintaining cross-temporal coherence. This formulation supports efficient time-bounded retrieval, hybrid semantic search, and lightweight structural reasoning in a single query path. A working prototype demonstrates scalable recall and contextual reinforcement using standard relational infrastructure, and we discuss extensions toward a columnar backend, distributed clustering, and emergent topic modeling.

Related papers

• MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents [2.808851478009314]
  Long-lived AI agents require continuity across interactions.<n> Continuity cannot be obtained by simply extending the prompt window.<n>We propose an architectural memory substrate organized along two axes.
  arXiv  Detail & Related papers  (2026-07-06T02:54:37Z)
• HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution [4.180315687162217]
  HAGE is a weighted multi-relational memory framework for agentic large language model (LLM) systems.<n>Given a query, an LLM-based classifier identifies the relational intent, and a routing network dynamically modulates the corresponding dimensions of the edge embedding.<n>Traversal scores are computed via a learned combination of semantic similarity and these query-conditioned edge representations.
  arXiv  Detail & Related papers  (2026-05-11T03:41:18Z)
• StructMem: Structured Memory for Long-Horizon Behavior in LLMs [32.74072149174656]
  StructMem is a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections.<n>By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on textttLoCoMo, while substantially reducing token usage, API calls, and runtime.
  arXiv  Detail & Related papers  (2026-04-23T14:57:23Z)
• Discrete Prototypical Memories for Federated Time Series Foundation Models [62.22804699052539]
  Leveraging Large Language Models as federated learning (FL)-based time series foundation models offers a promising way to transfer the generalization capabilities of LLMs to time series data.<n>However, the semantic misalignment between time-series data and the text-centric latent space of existing LLMs often leads to degraded performance.<n>We propose textscFeDPM, a federated framework for time-series foundation models based on discrete prototypical memories.
  arXiv  Detail & Related papers  (2026-04-06T06:57:08Z)
• Indaleko: The Unified Personal Index [0.0]
  dissertation presents the Unified Personal Index (UPI), a memory-aligned architecture that bridges this fundamental gap.<n>Indaleko prototype demonstrates the UPI's feasibility on a 31-million file dataset spanning 160TB across eight storage platforms.
  arXiv  Detail & Related papers  (2026-02-24T03:17:36Z)
• Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents [68.84161689205779]
  Temporal Semantic Memory (TSM) is a memory framework that models semantic time for point-wise memory.<n>TSM consistently outperforms existing methods and achieves up to 12.2% absolute improvement in accuracy.
  arXiv  Detail & Related papers  (2026-01-12T12:24:44Z)
• Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning [6.780460717949915]
  We introduce a temporal subgraph sampler that enhances global context by retrieving nodes beyond the immediate neighborhood.<n>We also propose Graph Perceiver (RGP), a graph transformer architecture for relational deep learning.<n>RGP delivers state-of-the-art performance, offering a general and scalable solution for relational deep learning.
  arXiv  Detail & Related papers  (2025-11-06T17:08:21Z)
• Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation [69.45495166424642]
  We develop a robust and discriminative QA benchmark to measure temporal, causal, and character consistency understanding in narrative documents.<n>We then introduce Entity-Event RAG (E2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping.<n>Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries.
  arXiv  Detail & Related papers  (2025-06-06T10:07:21Z)
• Fine-grained Attention in Hierarchical Transformers for Tabular Time-series [46.96700822457507]
  We propose Fieldy, a fine-grained hierarchical model that contextualizes fields at both the row and column levels. Our results show that combining row-wise and column-wise attention improves performance without increasing model size.
  arXiv  Detail & Related papers  (2024-06-21T17:40:46Z)
• More than Classification: A Unified Framework for Event Temporal Relation Extraction [61.44799147458621]
  Event temporal relation extraction(ETRE) is usually formulated as a multi-label classification task. We observe that all relations can be interpreted using the start and end time points of events. We propose a unified event temporal relation extraction framework, which transforms temporal relations into logical expressions of time points.
  arXiv  Detail & Related papers  (2023-05-28T02:09:08Z)
• HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning [59.38797474903334]
  This paper proposes the textbfHistorical textbfStructure textbfMatching (textbfHiSMatch) model. It applies two structure encoders to capture the semantic information contained in the historical structures of the query and candidate entities. Experiments on six benchmark datasets demonstrate the significant improvement of the proposed HiSMatch model, with up to 5.6% performance improvement in MRR, compared to the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-10-18T09:39:26Z)
• Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing [66.55478402233399]
  We propose a framework to elicit relational structures via a probing procedure based on Poincar'e distance metric. Compared with commonly-used rule-based methods for schema linking, we found that probing relations can robustly capture semantic correspondences. Our framework sets new state-of-the-art performance on three benchmarks.
  arXiv  Detail & Related papers  (2022-06-28T14:05:25Z)
• LaMemo: Language Modeling with Look-Ahead Memory [50.6248714811912]
  We propose Look-Ahead Memory (LaMemo) that enhances the recurrence memory by incrementally attending to the right-side tokens. LaMemo embraces bi-directional attention and segment recurrence with an additional overhead only linearly proportional to the memory length. Experiments on widely used language modeling benchmarks demonstrate its superiority over the baselines equipped with different types of memory.
  arXiv  Detail & Related papers  (2022-04-15T06:11:25Z)
• Topological Data Analysis of Database Representations for Information Retrieval [2.729524133721473]
  Persistent homology provides a rigorous characterization for the database topology. We show that some commonly used embeddings fail to preserve the connectivity. We introduce the dilation-invariant bottleneck distance to capture this effect.
  arXiv  Detail & Related papers  (2021-04-04T19:29:47Z)
• Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing [110.97778888305506]
  BRIDGE represents the question and DB schema in a tagged sequence where a subset of the fields are augmented with cell values mentioned in the question. BRIDGE attained state-of-the-art performance on popular cross-DB text-to- relational benchmarks. Our analysis shows that BRIDGE effectively captures the desired cross-modal dependencies and has the potential to generalize to more text-DB related tasks.
  arXiv  Detail & Related papers  (2020-12-23T12:33:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.