SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent

• URL: http://arxiv.org/abs/2607.22562v1
• Date: Fri, 29 May 2026 08:03:20 GMT
• Title: SF-AMS: Strategic Forgetting for Structured Memory in LLM Agent
• Abstract summary: This paper proposes a framework for maintaining compact high-utility memory by modeling the long-term importance of memory units.<n>SF-AMS replaces static retrieval and decay with a utility-driven survival mechanism that updates memory importance from redundancy usage and temporal signals.<n> Experiments on LoCoMo and LongMemEval-s show consistent gains over strong state of the art baselines including LightMemO Mem and A-Mem.
• Score: 23.56173571860151
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Managing long-context dependencies remains a primary bottleneck in LLM agents, as redundant and irrelevant information can degrade multi-step reasoning. Strategic Forgetting for Agent Memory Systems (SF-AMS) is proposed as a framework for maintaining compact high-utility memory by modeling the long-term importance of memory units. SF-AMS replaces static retrieval and heuristic decay with a utility-driven survival mechanism that updates memory importance from usage redundancy and temporal signals, inducing a hierarchical memory structure that prioritizes stable entity-consistent information while filtering noise. On top of this, Composite Importance Scoring integrates semantic and entity level signals to improve retrieval robustness. Experiments on LoCoMo and LongMemEval-s show consistent gains over strong state of the art baselines including LightMem MemO and A-Mem. The largest improvement appears in multi-hop reasoning under Qwen2.5-7B where SF-AMS achieves plus 9.65 F1 over the strongest baseline followed by temporal reasoning under GPT-4o-mini plus 6.91 F1 and open-domain tasks plus 6.53 F1 demonstrating strong cross backbone generalization. These results show that modeling memory importance as a dynamic utility signal is critical for reliable long-context reasoning.

Related papers

• Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents [39.55670043123564]
  Existing memory systems update memory when new information arrives.<n>Retrieval feedback is rarely exploited to reorganize memory for future access continuously.<n>We propose textbfREALM, a framework for continually evolving long-term memory in LLM agents.
  arXiv  Detail & Related papers  (2026-09-13T05:17:37Z)
• Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents [97.19033877543522]
  We present a controlled harness evaluation of memory substrates for memory-augmented agents.<n>We instrument 26 performance and efficiency metrics under a unified harness.<n>These findings motivate substrate routing as a necessary component of adaptive agent memory systems.
  arXiv  Detail & Related papers  (2026-08-15T03:29:48Z)
• 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)
• GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory [38.10762218232756]
  We introduce GRAVITY, a plug-and-play structured memory module.<n>It extracts three knowledge representations from raw conversational utterances.<n>It injects these representations into the host system's prompt as structured anchoring contexts.
  arXiv  Detail & Related papers  (2026-05-03T02:55:46Z)
• MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents [78.95081012334116]
  Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks.<n> contaminated or biased memory accumulation can trigger abnormal agent behaviors.<n>MemeEvoBench is the first benchmark evaluating memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.
  arXiv  Detail & Related papers  (2026-04-17T07:29:52Z)
• GAM: Hierarchical Graph-based Agentic Memory for LLM Agents [45.876418535406714]
  Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge.<n>Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient noise.<n>We propose GAM, a hierarchical Graph-based Agentic Memory framework that explicitly decouples memory encoding from consolidation.
  arXiv  Detail & Related papers  (2026-04-14T04:53:00Z)
• GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation [16.737829113782126]
  Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction.<n>Motivated by schema-based learning in cognitive neuroscience, we propose GAM-RAG, a training-free framework that accumulates retrieval experience from recurring or related queries.<n>GAM-RAG builds a lightweight, relation-free hierarchical index whose links capture potential co-occurrence rather than fixed semantic relations.
  arXiv  Detail & Related papers  (2026-03-02T12:09:17Z)
• From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents [78.30630000529133]
  We propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory.<n> MM-Mem memory structures hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic.<n>Experiments confirm the effectiveness of MM-Mem on both offline and streaming tasks.
  arXiv  Detail & Related papers  (2026-03-02T05:12:45Z)
• MemFly: On-the-Fly Memory Optimization via Information Bottleneck [35.420309099411874]
  Long-term memory enables large language model agents to tackle complex tasks through historical interactions.<n>Existing frameworks encounter a dilemma between compressing redundant information efficiently and maintaining precise retrieval for downstream tasks.<n>MemFly is a framework grounded in information bottleneck principles that facilitates on-the-fly memory evolution for LLMs.<n>MemFly substantially outperforms state-of-the-art baselines in memory coherence, response fidelity, and accuracy.
  arXiv  Detail & Related papers  (2026-02-08T09:37:25Z)
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
  Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
  arXiv  Detail & Related papers  (2026-01-05T08:24:16Z)
• Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling [83.29209853451697]
  Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs)<n>We introduce HGMem, a hypergraph-based memory mechanism that extends the concept of memory into a dynamic, expressive structure for complex reasoning and global understanding.<n>In our approach, memory is represented as a hypergraph whose hyperedges correspond to distinct memory units, enabling the progressive formation of higher-order interactions within memory.
  arXiv  Detail & Related papers  (2025-12-30T03:13:10Z)
• Memory-Augmented Log Analysis with Phi-4-mini: Enhancing Threat Detection in Structured Security Logs [0.0]
  We propose textbfDM-RAG, a dual-memory retrieval-augmented generation framework for structured log analysis.<n>It integrates a short-term memory buffer for recent summaries and a long-term FAISS-indexed memory for historical patterns.<n>On the UNSW-NB15 dataset, DM-RAG 53.64% accuracy and 98.70% recall, surpassing fine-tuned and RAG baselines in recall.
  arXiv  Detail & Related papers  (2025-10-01T05:23:05Z)
• Dynamic Memory-enhanced Transformer for Hyperspectral Image Classification [3.5093938502961763]
  Hyperspectral image (HSI) classification remains a challenging task due to the intricate spatial-spectral correlations.<n>Existing transformer models excel in capturing long-range dependencies but often suffer from information redundancy and attention inefficiencies.<n>MemFormer introduces a memory-enhanced multi-head attention mechanism that iteratively refines a dynamic memory module.<n>A dynamic memory enrichment strategy progressively captures complex spatial and spectral dependencies, leading to more expressive feature representations.
  arXiv  Detail & Related papers  (2025-04-17T17:43:34Z)

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.