StructMem: Structured Memory for Long-Horizon Behavior in LLMs

• URL: http://arxiv.org/abs/2604.21748v1
• Date: Thu, 23 Apr 2026 14:57:23 GMT
• Title: StructMem: Structured Memory for Long-Horizon Behavior in LLMs
• Abstract summary: 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.
• Score: 32.74072149174656
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat memory is efficient but fails to model relational structure, while graph-based memory enables structured reasoning at the cost of expensive and fragile construction. To address these issues, we propose \textbf{StructMem}, a structure-enriched hierarchical memory framework that preserves event-level bindings and induces cross-event connections. By temporally anchoring dual perspectives and performing periodic semantic consolidation, StructMem improves temporal reasoning and multi-hop performance on \texttt{LoCoMo}, while substantially reducing token usage, API calls, and runtime compared to prior memory systems, see https://github.com/zjunlp/LightMem .

Related papers

• MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents [9.22036278858962]
  We propose MemSIF (Memory with Structured Interactions and Facts), a structured interaction-to-fact memory framework.<n>MemSIF organizes raw interactions into Topical Segments that preserve local topical coherence and Event Traies that maintain cross-time event continuity.<n>MemSIF achieves the highest Total ACC in all settings, outperforming the strongest baseline by 2.29%-8.79% on LoCoMo and 2.87%-6.15% on LongMemEval-S.
  arXiv  Detail & Related papers  (2026-08-03T06:09:57Z)
• Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning [77.7531245219403]
  textscHomer is a Hierarchical Online Memory Exploration and Reasoning framework.<n>textscHomer's memory mirrors the multi-scale structure of long videos, ranging from raw perception, to recurring entities, to events connected by explicit temporal and causal relations.<n>textscHomer outperforms the previous best agent method by $+5.5$, $+10.8$, and $+4.4$ points on M3-Bench-robot, M3-Bench-web, and Video-MME-Long.
  arXiv  Detail & Related papers  (2026-07-01T05:53:09Z)
• REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs [17.526686616588794]
  Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons.<n>LLMs cannot retain all past interactions, making long-term memory management essential for storing, updating, and retrieving historical information.<n> REAL constructs long-term conversational memory as a temporal and confidence-aware directed property graph.
  arXiv  Detail & Related papers  (2026-06-09T10:53:10Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents [20.461904943047468]
  SegTreeMem represents conversation history as a temporally ordered Segment Tree over utterances.<n>For retrieval, SegTreeMem propagates relevance scores through the tree to combine local semantic matching with hierarchical temporal context.<n>Additional temporal-order permutation analysis shows that the performance gain depends on preserving temporal order during memory construction.
  arXiv  Detail & Related papers  (2026-06-03T07:42:15Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents [25.10969436399974]
  ES-Mem is a framework that partitions long-term interactions into semantically coherent events with distinct boundaries.<n>We show that ES-Mem yields consistent performance gains over baseline methods.<n>The proposed event segmentation module exhibits robust applicability on dialogue segmentation datasets.
  arXiv  Detail & Related papers  (2026-01-12T14:33:32Z)
• 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)
• Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning [14.368376032599437]
  Amory is a working memory framework that actively constructs structured memory representations during offline time.<n>Amory organizes conversational fragments into episodic narratives, consolidates memories with momentum, and semanticizes peripheral facts into semantic memory.<n>Amory achieves considerable improvements over previous state-of-the-art, with performance comparable to full context reasoning while reducing response time by 50%.
  arXiv  Detail & Related papers  (2026-01-09T19:51:11Z)
• Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning [55.251697395358285]
  Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments.<n>To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism that can retain, organize, and retrieve past experiences.<n>We propose CompassMem, an event-centric memory framework inspired by Event Theory.
  arXiv  Detail & Related papers  (2026-01-08T08:44:07Z)
• LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning [15.189701702660821]
  LiCoMemory is an end-to-end agentic memory framework for real-time updating and retrieval.<n>CoGraph is a lightweight hierarchical graph that utilizes entities and relations as semantic indexing layers.<n>Experiments on long-term dialogue benchmarks, LoCoMo and LongMemEval, show that LiCoMemory not only outperforms established baselines in temporal reasoning, multi-session consistency, and retrieval efficiency, but also notably reduces update latency.
  arXiv  Detail & Related papers  (2025-11-03T11:02:40Z)
• Evaluating Long-Term Memory for Long-Context Question Answering [100.1267054069757]
  We present a systematic evaluation of memory-augmented methods using LoCoMo, a benchmark of synthetic long-context dialogues annotated for question-answering tasks.<n>Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-27T18:03:50Z)

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.