Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory

• URL: http://arxiv.org/abs/2603.02473v1
• Date: Mon, 02 Mar 2026 23:47:23 GMT
• Title: Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory
• Abstract summary: We analyze how performance differences manifest across write strategies, retrieval methods, and memory utilization behavior.<n>On LoCoMo, retrieval method is the dominant factor.<n>Failure analysis shows that performance breakdowns most often manifest at the retrieval stage rather than at utilization.
• Score: 6.493102878734374
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Memory-augmented LLM agents store and retrieve information from prior interactions, yet the relative importance of how memories are written versus how they are retrieved remains unclear. We introduce a diagnostic framework that analyzes how performance differences manifest across write strategies, retrieval methods, and memory utilization behavior, and apply it to a 3x3 study crossing three write strategies (raw chunks, Mem0-style fact extraction, MemGPT-style summarization) with three retrieval methods (cosine, BM25, hybrid reranking). On LoCoMo, retrieval method is the dominant factor: average accuracy spans 20 points across retrieval methods (57.1% to 77.2%) but only 3-8 points across write strategies. Raw chunked storage, which requires zero LLM calls, matches or outperforms expensive lossy alternatives, suggesting that current memory pipelines may discard useful context that downstream retrieval mechanisms fail to compensate for. Failure analysis shows that performance breakdowns most often manifest at the retrieval stage rather than at utilization. We argue that, under current retrieval practices, improving retrieval quality yields larger gains than increasing write-time sophistication. Code is publicly available at https://github.com/boqiny/memory-probe.

Related papers

• Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering [42.31517185994942]
  RAG enables large language models to answer questions by accessing external knowledge.<n>Existing methods suffer from two key challenges: fragmented evidence scattered across temporally distant sessions, and noisy content within retrieved sessions that triggers the lost-in-the-middle effect.<n>We propose MemLoc, a unified Retrieve-Localize-Generate framework for long-term conversational memory QA.
  arXiv  Detail & Related papers  (2026-09-07T06:32:12Z)
• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents [63.38073530162493]
  Long-term memory helps agents reuse past experiences.<n> Static methods rely on fixed similaritys that do not optimize downstream utility.<n>We propose MERIT, a dynamic multi-horizon memory retrieval framework.
  arXiv  Detail & Related papers  (2026-05-30T05:44:34Z)
• MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents [10.248580356955085]
  Large Language Models (LLMs) have made significant progress in dialogue, yet redundant memory contexts limit their effectiveness.<n>We propose MGRetrieval, a retrieval strategy that grounds reflective retrieval in the semantic structure of historical memories.<n>Extensive experiments on LoCoMo show that MGRetrieval outperforms the strongest baseline by 8.91% in F1 and 11.11% in BLEU-1.
  arXiv  Detail & Related papers  (2026-05-22T14:41:56Z)
• iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation [10.824024745675281]
  iCoRe is an iterative, correlation-aware context retrieval approach.<n>Our method achieves a Fail-to-Pass rate of 42.0% and 52.8% respectively.
  arXiv  Detail & Related papers  (2026-04-21T08:26:30Z)
• MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning [78.46301394559903]
  Large Language Models (LLMs) are increasingly used for long-duration tasks.<n>Current methods face a trade-off between cost and accuracy.<n>MemSifter is a novel framework that offloads the memory retrieval process to a small-scale proxy model.
  arXiv  Detail & Related papers  (2026-03-03T02:57:38Z)
• NextMem: Towards Latent Factual Memory for LLM-based Agents [58.35585202907478]
  NextMem is a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory.<n>Extensive experiments demonstrate that NextMem achieves superior performance.
  arXiv  Detail & Related papers  (2026-02-26T14:35:27Z)
• Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval [37.055995647350784]
  This paper reproduces prior studies in document chunking and presents a systematic framework that unifies existing strategies.<n>Our evaluation reveals that optimal chunking strategies are task-dependent.
  arXiv  Detail & Related papers  (2026-02-19T00:27:15Z)
• SimpleMem: Efficient Lifelong Memory for LLM Agents [73.74399447715052]
  We introduce SimpleMem, an efficient memory framework based on semantic lossless compression.<n>We propose a three-stage pipeline designed to maximize information density and token utilization.<n> Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost.
  arXiv  Detail & Related papers  (2026-01-05T21:02:49Z)
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning [73.27233666920618]
  We propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it.<n>At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task.<n>We introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents.
  arXiv  Detail & Related papers  (2025-11-04T18:27:39Z)
• Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents [33.617262543252494]
  We present ReMemR1, a memory-augmented agent with callback-enhanced memory that allows selective retrieval from the entire memory history.<n>We also propose Reinforcement Learning with Multi-Level Rewards (RLMLR), which combines final-answer rewards with dense, step-level signals that guide effective memory use.
  arXiv  Detail & Related papers  (2025-09-27T01:36:46Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• A Gradient Accumulation Method for Dense Retriever under Memory Constraint [7.314901185604559]
  Contrastive Accumulation (ContAccum) is a stable and efficient memory reduction method for dense retriever trains. Experiments on widely used five information retrieval datasets indicate that ContAccum can surpass not only existing memory reduction methods but also high-resource scenario.
  arXiv  Detail & Related papers  (2024-06-18T07:41:11Z)
• RMM: Reinforced Memory Management for Class-Incremental Learning [102.20140790771265]
  Class-Incremental Learning (CIL) trains classifiers under a strict memory budget. Existing methods use a static and ad hoc strategy for memory allocation, which is often sub-optimal. We propose a dynamic memory management strategy that is optimized for the incremental phases and different object classes.
  arXiv  Detail & Related papers  (2023-01-14T00:07:47Z)
• Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval [49.98615945702959]
  We evaluate LTH and vector compression techniques for improving the downstream zero-shot retrieval accuracy of the TAS-B dense retriever. Our results demonstrate that, unlike prior work, LTH strategies when applied naively can underperform the zero-shot TAS-B dense retriever on average by up to 14% nDCG@10.
  arXiv  Detail & Related papers  (2022-05-23T17:53:44Z)
• Recall@k Surrogate Loss with Large Batches and Similarity Mixup [62.67458021725227]
  Direct optimization, by gradient descent, of an evaluation metric is not possible when it is non-differentiable. In this work, a differentiable surrogate loss for the recall is proposed. The proposed method achieves state-of-the-art results in several image retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-08-25T11:09:11Z)

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.