Imagen de Portada

Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuan, Boqin, Su, Yue, Yao, Kun
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation
por: Yuan, Boqin, et al.
Publicado: (2026)

L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search
por: Wang, Ziqi, et al.
Publicado: (2025)

SimpleMem: Efficient Lifelong Memory for LLM Agents
por: Liu, Jiaqi, et al.
Publicado: (2026)

RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation
por: Yuan, Haonan, et al.
Publicado: (2026)

Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
por: Yuen, Sizhe, et al.
Publicado: (2025)

MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
por: Gao, Yicheng, et al.
Publicado: (2026)

MemR$^3$: Memory Retrieval via Reflective Reasoning for LLM Agents
por: Du, Xingbo, et al.
Publicado: (2025)

RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents
por: Kagaya, Tomoyuki, et al.
Publicado: (2024)

MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
por: Sidik, Bronislav, et al.
Publicado: (2026)

D-Mem: A Dual-Process Memory System for LLM Agents
por: You, Zhixing, et al.
Publicado: (2026)

Unveiling Privacy Risks in LLM Agent Memory
por: Wang, Bo, et al.
Publicado: (2025)

Uncovering Bottlenecks and Optimizing Scientific Lab Workflows with Cycle Time Reduction Agents
por: Fehlis, Yao
Publicado: (2025)

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents
por: Shen, Yiting, et al.
Publicado: (2026)

Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
por: Li, Xiaozhe, et al.
Publicado: (2026)

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
por: Fan, Linfeng, et al.
Publicado: (2026)

An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation
por: Zhu, Kun, et al.
Publicado: (2024)

Bottleneck Tokens for Unified Multimodal Retrieval
por: Sun, Siyu, et al.
Publicado: (2026)

Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory
por: Sadowski, Albert, et al.
Publicado: (2026)

RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation
por: Anh, Le Vu, et al.
Publicado: (2025)

What Deserves Memory: Adaptive Memory Distillation for LLM Agents
por: Ma, Wenquan, et al.
Publicado: (2025)

Memory Intelligence Agent
por: Qiao, Jingyang, et al.
Publicado: (2026)

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents
por: Su, Miao, et al.
Publicado: (2026)

Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles
por: Yan, Lu, et al.
Publicado: (2026)

Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers
por: Li, Quanhao, et al.
Publicado: (2026)

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
por: Shi, Wei, et al.
Publicado: (2026)

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents
por: Zhang, Xiaohui, et al.
Publicado: (2026)

On the Structural Memory of LLM Agents
por: Zeng, Ruihong, et al.
Publicado: (2024)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
por: Srivastava, Saksham Sahai, et al.
Publicado: (2025)

Revisiting LLM Reasoning via Information Bottleneck
por: Lei, Shiye, et al.
Publicado: (2025)

Attention Saturation and Gradient Suppression at Inflection Layers: Diagnosing and Mitigating Bottlenecks in Transformer Adaptation
por: Zixian, Wang
Publicado: (2025)

On Memory Construction and Retrieval for Personalized Conversational Agents
por: Pan, Zhuoshi, et al.
Publicado: (2025)

AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
por: Zhao, Yujie, et al.
Publicado: (2026)

Towards Autonomous Memory Agents
por: Wu, Xinle, et al.
Publicado: (2026)

Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
por: Tartaglini, Alexa R., et al.
Publicado: (2025)

ABBEL: LLM Agents Acting through Belief Bottlenecks Expressed in Language
por: Lidayan, Aly, et al.
Publicado: (2025)

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
por: Fan, Shengda, et al.
Publicado: (2026)

Lightweight LLM Agent Memory with Small Language Models
por: Zhang, Jiaquan, et al.
Publicado: (2026)

Coarse-to-Fine Grounded Memory for LLM Agent Planning
por: Yang, Wei, et al.
Publicado: (2025)

Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows
por: Gharzeddine, Luay, et al.
Publicado: (2026)

AIRA_2: Overcoming Bottlenecks in AI Research Agents
por: Hambardzumyan, Karen, et al.
Publicado: (2026)